© 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. 87840
    Prev
    Next
    INDEX
    Explanations

    connecting phrases and references in academic or analytical 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
    aign
    -0.08
    rahim
    -0.07
    ycz
    -0.06
    ourn
    -0.06
    lh
    -0.06
    ignKey
    -0.06
    hani
    -0.06
    ombo
    -0.06
    hev
    -0.06
    arel
    -0.06
    POSITIVE LOGITS
     Append
    0.08
     also
    0.07
     append
    0.07
    also
    0.07
     także
    0.06
    -append
    0.06
     Apps
    0.06
     Applications
    0.06
    омеÑĢ
    0.06
     pornstar
    0.06
    Activations Density 0.006%

    No Known Activations