© 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. 119186
    Prev
    Next
    INDEX
    Explanations

    references to legislative acts and their implications

    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
    ouv
    -0.08
    loff
    -0.08
    agina
    -0.07
    erais
    -0.07
    upos
    -0.07
    roleum
    -0.07
    _ord
    -0.07
    áng
    -0.07
    abd
    -0.07
    lical
    -0.07
    POSITIVE LOGITS
     “[
    0.07
    :↵↵↵↵↵↵
    0.07
     writes
    0.06
    pod
    0.06
     "[
    0.06
    ¬
    0.06
     wrote
    0.06
     Dudley
    0.06
    maf
    0.06
     crow
    0.05
    Activations Density 0.113%

    No Known Activations