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. 125598
    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
    WND
    -0.09
    TOTYPE
    -0.07
    -await
    -0.07
    orex
    -0.07
    Ā
    -0.07
     spol
    -0.07
    طاÙĤ
    -0.07
    porte
    -0.07
    าม
    -0.07
    اÙ
    -0.07
    POSITIVE LOGITS
     Www
    0.07
     fucking
    0.06
     FUCK
    0.06
     fuck
    0.06
     Fuck
    0.06
    Äįe
    0.06
    it
    0.06
    ete
    0.06
     -
    0.06
     PR
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.