© 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. 57551
    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
    ¶Į
    -0.07
    lisi
    -0.07
    åºľ
    -0.07
     ï¼ľ
    -0.06
    pear
    -0.06
    ĤŃ
    -0.06
    बल
    -0.06
    ĶĶ
    -0.06
    jang
    -0.06
     tup
    -0.06
    POSITIVE LOGITS
    eten
    0.07
    ieux
    0.07
    iko
    0.06
    bian
    0.06
    iel
    0.06
    ogne
    0.06
    yles
    0.06
    447
    0.06
    plat
    0.06
    ork
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.