© 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. 40109
    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
    aler
    -0.08
    áºŃy
    -0.07
    398
    -0.06
    inus
    -0.06
    STANCE
    -0.06
    赤
    -0.06
    ATAR
    -0.06
    asy
    -0.06
     Happiness
    -0.06
     Emin
    -0.06
    POSITIVE LOGITS
    OperationException
    0.07
    onnen
    0.06
    ather
    0.06
    ypi
    0.06
    istrovstvÃŃ
    0.06
     Lair
    0.06
     fandom
    0.06
    /ion
    0.06
    ariant
    0.06
    isin
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.