© 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 EvalsExportsAPI 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. 87515
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly references or citations

    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
    _tF
    -0.07
    Looper
    -0.07
    npos
    -0.07
    enes
    -0.07
    orde
    -0.07
    elles
    -0.07
    ergy
    -0.07
    .shiro
    -0.07
     деÑĢ
    -0.06
    /uploads
    -0.06
    POSITIVE LOGITS
     Authorities
    0.07
    Authorities
    0.06
    vinc
    0.06
     page
    0.06
    emann
    0.06
     authorities
    0.06
     alongside
    0.05
     NOP
    0.05
     Kens
    0.05
     Supply
    0.05
    Activations Density 0.023%

    No Known Activations