© 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. 5-LLAMASCOPE-RES-131K
    11. 126540
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "described" to indicate characterization or attribution of qualities to subjects

    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
    adar
    -0.07
     Ashley
    -0.07
    consin
    -0.06
     wallet
    -0.06
    ToProps
    -0.06
    df
    -0.06
    lette
    -0.06
    duk
    -0.06
    elia
    -0.06
    doch
    -0.06
    POSITIVE LOGITS
    ´
    0.07
    ãĥ¼ãĤ¹ãĥĪ
    0.07
    ANGO
    0.06
    onga
    0.06
    ango
    0.06
     ç¬
    0.06
     СÑĥд
    0.06
    _HERSHEY
    0.06
    jed
    0.06
    SessionFactory
    0.06
    Activations Density 0.011%

    No Known Activations