© 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. 57698
    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
    .scalablytyped
    -0.11
    égor
    -0.08
    ndern
    -0.08
    uib
    -0.07
    odor
    -0.07
    idUser
    -0.07
     {{--<
    -0.07
    amarin
    -0.07
    áºŃn
    -0.07
     STATS
    -0.07
    POSITIVE LOGITS
     Lorem
    0.07
    atas
    0.06
     people
    0.06
     t
    0.06
     (
    0.06
    dux
    0.05
     Rodriguez
    0.05
     grain
    0.05
     character
    0.05
     Complaint
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.