© 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. 83139
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting symbols within code or text

    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
    876
    -0.06
    xt
    -0.06
    den
    -0.06
    Table
    -0.06
    386
    -0.06
    si
    -0.06
     Attention
    -0.05
    sc
    -0.05
    074
    -0.05
    anc
    -0.05
    POSITIVE LOGITS
    omnia
    0.08
    avan
    0.07
    bery
    0.07
    osto
    0.07
    bero
    0.07
     Lind
    0.06
    ç´ł
    0.06
    çºĮ
    0.06
     ØŃÙĪÙĦ
    0.06
    ossier
    0.06
    Activations Density 0.001%

    No Known Activations