© 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. 40342
    Prev
    Next
    INDEX
    Explanations

    instances of the word "The" in varying contexts of sentences

    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
    :
    -0.09
    ...
    -0.08
    .
    -0.07
    ↵
    -0.07
     via
    -0.07
    -
    -0.07
    ,
    -0.07
    ;
    -0.07
    ..
    -0.07
     respectively
    -0.07
    POSITIVE LOGITS
    raison
    0.11
    inclu
    0.10
    âĢ¦"↵↵
    0.10
    Äįel
    0.10
    oret
    0.10
    âĢ¦.↵↵
    0.09
    aida
    0.09
    (EXPR
    0.09
    /Gate
    0.09
    /Dk
    0.09
    Activations Density 0.062%

    No Known Activations