© 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. 3736
    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
    uter
    -0.07
    ues
    -0.06
    istani
    -0.06
    isz
    -0.06
     oc
    -0.06
    ãĥĬãĥ¼
    -0.06
    ieri
    -0.06
    pane
    -0.06
    cia
    -0.06
    iac
    -0.06
    POSITIVE LOGITS
    _usec
    0.07
     serialVersionUID
    0.07
    ftware
    0.06
    нÑĸвеÑĢ
    0.06
    oth
    0.06
    anel
    0.06
     isFirst
    0.06
    CLE
    0.06
    hte
    0.06
    opa
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.