© 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. 74688
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a disclaimer or cautionary note

    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
    ↵
    -0.06
     -
    -0.06
    uffman
    -0.06
     architect
    -0.06
     dog
    -0.06
     Bart
    -0.05
    p
    -0.05
     Rh
    -0.05
     rh
    -0.05
    is
    -0.05
    POSITIVE LOGITS
    ç¬
    0.09
    NewProp
    0.08
    actionDate
    0.08
    ylko
    0.08
    erland
    0.08
    _MetaData
    0.08
    itzer
    0.08
    abler
    0.08
    LTRB
    0.07
    iyim
    0.07
    Activations Density 0.003%

    No Known Activations