© 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. 5-LLAMASCOPE-RES-131K
    11. 126644
    Prev
    Next
    INDEX
    Explanations

    terms related to flaws or inadequacies

    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
    geç
    -0.07
    ottage
    -0.07
    oir
    -0.07
    <?,
    -0.06
    ضÛĮ
    -0.06
    igi
    -0.06
    ToSend
    -0.06
    bjerg
    -0.06
    gia
    -0.06
    Ä±ÅŁÄ±k
    -0.06
    POSITIVE LOGITS
    reds
    0.07
    /loose
    0.06
     Weinstein
    0.06
     Kushner
    0.06
    asse
    0.06
    ainen
    0.06
    /Peak
    0.06
    ment
    0.06
    slaught
    0.06
     circ
    0.06
    Activations Density 0.005%

    No Known Activations