© 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. 40740
    Prev
    Next
    INDEX
    Explanations

    references to percentages and statistical data

    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
    ê´
    -0.07
    üçük
    -0.07
    Äįka
    -0.07
    cÃŃm
    -0.06
    çķ
    -0.06
    opp
    -0.06
    ozÃŃ
    -0.06
    âĤ¬“
    -0.06
    drawing
    -0.06
    amma
    -0.06
    POSITIVE LOGITS
    ile
    0.08
    ake
    0.08
    ita
    0.08
     chance
    0.07
    umba
    0.07
     increase
    0.07
     discount
    0.07
    785
    0.06
    .scalar
    0.06
    ỡ
    0.06
    Activations Density 0.030%

    No Known Activations