© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89362
    Prev
    Next
    INDEX
    Explanations

    references to job roles and employment in the context of government or public service positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Prepositions and articles that connect job titles, roles, or positions with the specific occupation or workplace, often in biographical contexts describing career progressions. Common patterns include "as a/the/an [job title]", "from [starting role] to [advanced role]", or job descriptions joined by conjunctions like "and" or "or".

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ixin
    -0.09
     обл
    -0.07
    è¶Ĭ
    -0.07
    dana
    -0.07
    ikat
    -0.07
    amarin
    -0.07
    cee
    -0.07
     deduct
    -0.07
    ded
    -0.06
    ission
    -0.06
    POSITIVE LOGITS
     cler
    0.07
     assist
    0.07
     admin
    0.07
    ola
    0.06
     Robertson
    0.06
     Loading
    0.06
     manually
    0.06
     manual
    0.06
     grunt
    0.06
    á»įn
    0.06
    Activations Density 0.311%

    No Known Activations