© 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. 5-LLAMASCOPE-RES-131K
    6. 126563
    Prev
    Next
    INDEX
    Explanations

    expressions of confusion or uncertainty

    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
    ANDOM
    -0.06
    hips
    -0.06
    COPY
    -0.06
    éĻ¢
    -0.06
    æŃ
    -0.06
    able
    -0.06
    actable
    -0.06
    ham
    -0.06
    -devel
    -0.06
     encyclopedia
    -0.06
    POSITIVE LOGITS
    ixo
    0.08
    IOD
    0.07
    ê¹
    0.07
    ’ya
    0.07
    ppy
    0.06
    aji
    0.06
    /false
    0.06
    udit
    0.06
    atta
    0.06
    ngr
    0.06
    Activations Density 0.001%

    No Known Activations