© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98962
    Prev
    Next
    INDEX
    Explanations

    names or identities associated with individuals

    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
    RuntimeObject
    -0.08
    phem
    -0.07
    æ®Ĭ
    -0.07
    stvo
    -0.07
    ERSHEY
    -0.07
    ANNEL
    -0.07
     requestOptions
    -0.07
    cou
    -0.07
    viÄį
    -0.07
     mdi
    -0.07
    POSITIVE LOGITS
    551
    0.06
     mach
    0.06
    ãĤ¡
    0.06
     interf
    0.06
     at
    0.06
     paralle
    0.06
     Tu
    0.06
     Y
    0.06
     n
    0.05
     S
    0.05
    Activations Density 0.003%

    No Known Activations