© 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. 118878
    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
    registers
    -0.08
    agara
    -0.08
     WINAPI
    -0.07
    .)↵↵↵↵
    -0.07
    frauen
    -0.07
    rej
    -0.07
    Ø®ÙĬ
    -0.07
    èn
    -0.07
    radient
    -0.07
    _literals
    -0.07
    POSITIVE LOGITS
    owl
    0.07
    lyn
    0.06
    WithValue
    0.06
     Dante
    0.06
    egment
    0.05
     fro
    0.05
    udden
    0.05
    895
    0.05
    dit
    0.05
    part
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.