© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57690
    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
    420
    -0.07
    edor
    -0.06
    arend
    -0.06
    evin
    -0.06
    uro
    -0.06
    iment
    -0.06
    atal
    -0.06
     xen
    -0.06
    311
    -0.06
    rik
    -0.06
    POSITIVE LOGITS
    obia
    0.07
     drip
    0.07
    .Invariant
    0.06
    upa
    0.06
     desar
    0.06
    ãĢģãĢģ
    0.06
    Ordinal
    0.06
    .clients
    0.06
    reib
    0.06
    odesk
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.