© 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. 16149
    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
    ules
    -0.06
     terminals
    -0.06
    ög
    -0.06
     Authorities
    -0.06
     Priv
    -0.06
     Hell
    -0.05
    uci
    -0.05
    forman
    -0.05
     cock
    -0.05
     authorities
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĥIJ
    0.07
    /copyleft
    0.07
    aeper
    0.07
     FileType
    0.07
    .setViewport
    0.06
    isor
    0.06
    nore
    0.06
     realpath
    0.06
    \.
    0.06
     Classified
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.