© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84543
    Prev
    Next
    INDEX
    Explanations

    actions aimed at hindering or obstructing progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     اÙĦرسÙħÙĬ
    -0.06
    Boolean
    -0.06
    837
    -0.06
    AINER
    -0.06
    ESH
    -0.06
    mh
    -0.06
    913
    -0.06
    esh
    -0.06
    ail
    -0.06
    locker
    -0.06
    POSITIVE LOGITS
     attempts
    0.11
     Attempts
    0.08
    tempts
    0.08
     efforts
    0.08
     attempt
    0.08
     progress
    0.07
     plans
    0.07
    /disable
    0.07
     Attempt
    0.07
    Duplicates
    0.06
    Activations Density 0.027%

    No Known Activations