© 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. 93618
    Prev
    Next
    INDEX
    Explanations

    changes and updates in information

    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
    Ñľ
    -0.07
    iss
    -0.06
    hus
    -0.06
     ç½
    -0.06
     Garrett
    -0.05
    outers
    -0.05
     Classified
    -0.05
     trib
    -0.05
    un
    -0.05
    ÐIJÐł
    -0.05
    POSITIVE LOGITS
     accordingly
    0.12
     update
    0.09
     Update
    0.07
     updating
    0.07
     updates
    0.07
    /update
    0.07
    ercul
    0.07
    tgt
    0.07
    æĽ´æĸ°
    0.07
    :update
    0.07
    Activations Density 0.016%

    No Known Activations