© 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. 71441
    Prev
    Next
    INDEX
    Explanations

    phrases that include conjunctions used for elaboration or addition

    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
     {}.
    -0.07
    onte
    -0.07
    icari
    -0.07
    >).
    -0.06
    )).
    -0.06
    }.
    -0.06
     æī
    -0.06
    abwe
    -0.06
     will
    -0.06
    iec
    -0.06
    POSITIVE LOGITS
    !!,
    0.09
     _______,
    0.09
     [],
    0.07
     ?,
    0.07
    !,
    0.07
     (),
    0.07
    ,[
    0.07
    ?,↵
    0.07
    iqueta
    0.07
    ?,
    0.07
    Activations Density 0.088%

    No Known Activations