© 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. 17-LLAMASCOPE-RES-131K
    11. 118415
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistics within the text

    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
    ĵåIJį
    -0.07
    ahan
    -0.06
    emme
    -0.06
    166
    -0.06
    èĪ
    -0.06
    itel
    -0.06
     terms
    -0.06
    esthetic
    -0.06
     fog
    -0.06
    imary
    -0.06
    POSITIVE LOGITS
     ÎĶE
    0.07
    zk
    0.06
    ifer
    0.06
    -envelope
    0.06
     æ¶
    0.06
     Newman
    0.06
     ged
    0.06
    -pencil
    0.06
    owns
    0.06
     Encode
    0.06
    Activations Density 0.002%

    No Known Activations