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. 125758
    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
    818
    -0.06
     Confidential
    -0.06
    ulis
    -0.06
     createState
    -0.06
    asje
    -0.06
     Turnbull
    -0.06
     Guar
    -0.06
    _ARG
    -0.06
    даÑĤ
    -0.06
    318
    -0.06
    POSITIVE LOGITS
    Campaign
    0.08
     campaign
    0.08
     Campaign
    0.08
     campaigns
    0.07
     FEC
    0.07
    eczy
    0.07
    .Apis
    0.07
    åĢĻ
    0.07
    _campaign
    0.07
    ozilla
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.