© 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. 15-LLAMASCOPE-RES-131K
    11. 90397
    Prev
    Next
    INDEX
    Explanations

    nouns and their related concepts that imply organized activities or relationships

    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
    allet
    -0.07
     Olson
    -0.06
    agna
    -0.06
     comb
    -0.06
    inton
    -0.06
     Thi
    -0.06
    611
    -0.06
    /or
    -0.06
    askell
    -0.06
    istra
    -0.06
    POSITIVE LOGITS
    inea
    0.07
    ,'#
    0.07
    anst
    0.06
    енÑģ
    0.06
    aked
    0.06
    iner
    0.06
    .HTML
    0.06
    ars
    0.06
    akes
    0.06
    dÃŃ
    0.06
    Activations Density 0.023%

    No Known Activations