Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 57294
    Prev
    Next
    INDEX
    Explanations

    advertising or promotional materials

    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
    UST
    -0.07
    zon
    -0.06
     Diary
    -0.06
    arching
    -0.06
    ked
    -0.06
    yar
    -0.06
     Dek
    -0.06
    597
    -0.05
    932
    -0.05
    608
    -0.05
    POSITIVE LOGITS
    ICATION
    0.08
    /cards
    0.08
    Languages
    0.08
    eprom
    0.07
    iat
    0.07
     vitae
    0.07
    -pdf
    0.07
    endir
    0.07
    æ¡Ī
    0.07
    ILE
    0.07
    Activations Density 0.009%

    No Known Activations