© 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. 76139
    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
     trim
    -0.07
     respective
    -0.06
    /*č↵
    -0.06
    OrDefault
    -0.06
    íħ
    -0.06
    "./
    -0.06
    Trim
    -0.06
    LESS
    -0.06
    #__
    -0.06
    andas
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.07
    bst
    0.07
    @Id
    0.07
    /lang
    0.07
    iyel
    0.07
    _mB
    0.07
    ména
    0.07
    keh
    0.07
    _tE
    0.06
    ingleton
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.