© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126046
    Prev
    Next
    INDEX
    Explanations

    requests for information or action

    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
    _WS
    -0.07
    ãĤ
    -0.07
    ška
    -0.07
    achs
    -0.07
    endor
    -0.06
    immers
    -0.06
    alus
    -0.06
    ONENT
    -0.06
    Ø
    -0.06
    ania
    -0.06
    POSITIVE LOGITS
     consult
    0.10
     refer
    0.10
     visit
    0.09
    visit
    0.08
    refer
    0.07
     contact
    0.07
     consultar
    0.07
     REFER
    0.07
     consultation
    0.07
     consulted
    0.06
    Activations Density 0.006%

    No Known Activations