© 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. 3901
    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
    #ac
    -0.07
     Flake
    -0.07
    aea
    -0.07
    #aa
    -0.06
    enson
    -0.06
    nad
    -0.06
    ceans
    -0.06
    aja
    -0.06
    unc
    -0.06
    _adc
    -0.06
    POSITIVE LOGITS
    ucid
    0.08
    inet
    0.07
    uki
    0.07
    PMC
    0.07
    Staff
    0.06
    adge
    0.06
    RAINT
    0.06
    é³
    0.06
     KÄį
    0.06
    irebase
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.