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. 82950
    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
    agal
    -0.08
    agner
    -0.07
    еÑĢÑĪ
    -0.07
    кÑĢеÑĤ
    -0.07
    inci
    -0.07
    .gnu
    -0.07
    олж
    -0.07
     заÑĤ
    -0.07
    ventus
    -0.06
    ometer
    -0.06
    POSITIVE LOGITS
    odont
    0.07
     Bod
    0.07
    udent
    0.06
    /www
    0.05
     zbo
    0.05
    sett
    0.05
     Dag
    0.05
    éłĺ
    0.05
     prosper
    0.05
     springfox
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.