© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17825
    Prev
    Next
    INDEX
    Explanations

    references to roles and factors influencing outcomes

    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
    ISC
    -0.07
    ç·ł
    -0.07
    _registro
    -0.07
    ãĥĭãĥ¡
    -0.07
     SUBSTITUTE
    -0.07
    StateMachine
    -0.07
    ÏĮÏĦηÏĦαÏĤ
    -0.07
    artin
    -0.07
    esses
    -0.07
    arra
    -0.07
    POSITIVE LOGITS
     why
    0.09
    adro
    0.07
    0.06
     parte
    0.06
     factors
    0.06
     Aid
    0.06
     behind
    0.06
     too
    0.06
     this
    0.06
     div
    0.06
    Activations Density 0.015%

    No Known Activations