© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27458
    Prev
    Next
    INDEX
    Explanations

    instances of exceptional qualities or noteworthy attributes in various contexts

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

    Words and phrases that appear in various semantic contexts, without a clear unifying pattern beyond being ordinary linguistic elements.

    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
    NamedQuery
    -0.07
    hani
    -0.07
    abal
    -0.07
    .forName
    -0.06
    ãĥĭãĥ¼
    -0.06
    uggling
    -0.06
    ErrMsg
    -0.06
    aney
    -0.06
    nung
    -0.06
    propri
    -0.06
    POSITIVE LOGITS
    sian
    0.06
     PROCUREMENT
    0.06
    _NOTIFICATION
    0.06
    appen
    0.06
    湿
    0.06
    до
    0.06
    012
    0.06
    emek
    0.05
     Bid
    0.05
    spd
    0.05
    Activations Density 0.020%

    No Known Activations