© 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. 78239
    Prev
    Next
    INDEX
    Explanations

    connection and coordination in social contexts

    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
    estone
    -0.08
    agan
    -0.07
    inger
    -0.06
    ppard
    -0.06
     impress
    -0.06
    ãĥ¬ãĥĵ
    -0.06
    x
    -0.06
    дап
    -0.05
     Rhino
    -0.05
    &
    -0.05
    POSITIVE LOGITS
    HttpException
    0.07
    _Exception
    0.07
    ór
    0.07
    uct
    0.07
    /pub
    0.07
    .scalablytyped
    0.07
    омеÑĢ
    0.06
    δÏĮ
    0.06
    anst
    0.06
    ":[{↵
    0.06
    Activations Density 0.000%

    No Known Activations