© 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. 126474
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ynet
    -0.08
    ازÙĨد
    -0.07
     '&'
    -0.07
    ENDOR
    -0.07
    óng
    -0.07
    ÅĤo
    -0.07
    رÙī
    -0.07
     bát
    -0.07
    opsis
    -0.07
    pek
    -0.07
    POSITIVE LOGITS
    ê°Ħ
    0.06
    bas
    0.05
    MAS
    0.05
    olle
    0.05
    unt
    0.05
    uitka
    0.05
     Brut
    0.05
     Phoenix
    0.05
    BN
    0.05
     Silent
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.