© 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. 118946
    Prev
    Next
    INDEX
    Explanations

    references to the word "Silver."

    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
    688
    -0.07
    eful
    -0.07
    çķ
    -0.07
    ergarten
    -0.07
    leri
    -0.07
    _MALLOC
    -0.07
    ulp
    -0.07
    ismic
    -0.06
    sj
    -0.06
    rael
    -0.06
    POSITIVE LOGITS
    -grey
    0.09
    stein
    0.09
    -white
    0.07
    ħ§
    0.07
    -gray
    0.07
    ado
    0.07
     Ag
    0.07
    stone
    0.07
    -haired
    0.07
     Mobil
    0.07
    Activations Density 0.006%

    No Known Activations