© 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. 3823
    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
     Rowe
    -0.08
    ipher
    -0.07
    aint
    -0.07
    implify
    -0.07
    oningen
    -0.07
    olygon
    -0.07
    олее
    -0.07
    [".
    -0.06
    awi
    -0.06
    Anywhere
    -0.06
    POSITIVE LOGITS
     Stateless
    0.07
    IFA
    0.06
    ocado
    0.06
     Marin
    0.06
    !..
    0.06
    âĺħâĺħ
    0.06
    té
    0.06
     çģ
    0.06
    :///
    0.05
    åIJ
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.