© 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. 118586
    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
    üh
    -0.07
    .ci
    -0.07
    OnInit
    -0.06
    [image
    -0.06
    @d
    -0.06
    (íģ¬ê¸°
    -0.06
    Ùħار
    -0.06
    [text
    -0.06
     fucking
    -0.06
     tow
    -0.06
    POSITIVE LOGITS
    ense
    0.07
    utoff
    0.07
    Fmt
    0.07
    ırak
    0.07
    deniz
    0.06
    ones
    0.06
    æŁĵ
    0.06
     FIXME
    0.06
     :-
    0.06
    lek
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.