© 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. 126765
    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
    626
    -0.06
     ch
    -0.06
    833
    -0.06
    zp
    -0.06
    ↵
    -0.06
    s
    -0.06
     Rew
    -0.06
    iode
    -0.06
    398
    -0.06
    ion
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.10
    iyim
    0.09
     rast
    0.07
    criptor
    0.07
    allon
    0.07
    childs
    0.07
     Alv
    0.07
    dre
    0.07
    -cols
    0.07
    اÙĤ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.