© 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. 129218
    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
    gettext
    -0.07
    arie
    -0.07
    _HC
    -0.06
     jint
    -0.06
    akit
    -0.06
    å¼Ĥ
    -0.06
    245
    -0.06
     globals
    -0.06
    aut
    -0.06
    progressbar
    -0.06
    POSITIVE LOGITS
    ̣
    0.07
    stagram
    0.07
    uded
    0.06
    .scalablytyped
    0.06
    uffman
    0.06
     Cust
    0.06
    änd
    0.06
    guards
    0.06
    ipse
    0.06
    eldon
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.