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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77438
    Prev
    Next
    INDEX
    Explanations

    references to automated production and AI technology

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

    Words or phrases that mark significant transition points in text, often appearing at boundaries between content sections or preceding punctuation marks that separate different text segments.

    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
     sel
    -0.08
    sel
    -0.07
    ("(%
    -0.07
    noinspection
    -0.06
    erken
    -0.06
    FO
    -0.06
     Peters
    -0.06
    spor
    -0.06
    راÙĩ
    -0.06
    .chapter
    -0.06
    POSITIVE LOGITS
     output
    0.08
    usercontent
    0.07
    iam
    0.07
     AI
    0.07
     gener
    0.07
     tiener
    0.06
     Chat
    0.06
    output
    0.06
     outputs
    0.06
     Verfüg
    0.06
    Activations Density 0.002%

    No Known Activations