© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128754
    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
    zung
    -0.07
     study
    -0.07
    ensa
    -0.06
     stro
    -0.06
     &
    -0.06
     hipp
    -0.06
     bois
    -0.05
     nihil
    -0.05
    liers
    -0.05
    prung
    -0.05
    POSITIVE LOGITS
    atform
    0.08
    Ral
    0.07
    umi
    0.07
    .defaults
    0.07
    OptionsResolver
    0.07
    æŁĦ
    0.07
    utt
    0.07
     Nack
    0.06
    Arrow
    0.06
    oggle
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.