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. 29204
    Prev
    Next
    INDEX
    Explanations

    references to cancer support services and the connections among patients, their families, and healthcare professionals

    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
    ç©´
    -0.08
     @$_
    -0.07
    eprom
    -0.07
    á»ijng
    -0.07
    aksi
    -0.07
    etting
    -0.07
    swick
    -0.07
    ::<
    -0.07
    TAG
    -0.07
    /goto
    -0.07
    POSITIVE LOGITS
     chat
    0.08
    -chat
    0.07
     consult
    0.07
    /chat
    0.07
     conc
    0.07
     chatting
    0.06
     sessions
    0.06
     virtual
    0.06
    atern
    0.06
     Conc
    0.06
    Activations Density 0.006%

    No Known Activations