Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84209
    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
    ierre
    -0.06
    ence
    -0.05
    icz
    -0.05
    /database
    -0.05
     train
    -0.05
     viewing
    -0.05
    ingham
    -0.05
     conventional
    -0.05
    éĸ
    -0.05
     unconventional
    -0.05
    POSITIVE LOGITS
    ãĥ¼ãĥĦ
    0.07
     )))
    0.07
    ettings
    0.07
    chyb
    0.07
    ãĤīãģĹ
    0.07
    ÑĥнкÑĤ
    0.07
    }elseif
    0.07
    ifar
    0.07
    vů
    0.07
    _ASSUME
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.