© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3356
    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
    tiler
    -0.07
    &m
    -0.07
    ALLE
    -0.07
    idot
    -0.07
    ahlen
    -0.07
    semb
    -0.06
    imler
    -0.06
    esin
    -0.06
    ادÙĩ
    -0.06
    erli
    -0.06
    POSITIVE LOGITS
    öh
    0.07
    ÑĥÑħ
    0.06
    ãģĸ
    0.06
    ãĥ¥
    0.06
    浩
    0.06
    ãĤ·ãĥ¼
    0.06
    Ñĥй
    0.06
    sal
    0.06
    du
    0.06
    WithContext
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.