© 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. 15-LLAMASCOPE-RES-131K
    11. 980
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and liability statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ools
    -0.08
    issen
    -0.07
    erah
    -0.07
    imbus
    -0.07
     Khal
    -0.06
    ijken
    -0.06
    erus
    -0.06
    abbo
    -0.06
    datable
    -0.06
    аÑĤков
    -0.06
    POSITIVE LOGITS
    ams
    0.07
     loss
    0.06
     losses
    0.06
    mal
    0.06
     damages
    0.06
    .slim
    0.06
     INDIRECT
    0.06
    loss
    0.06
     queryInterface
    0.06
    _Register
    0.06
    Activations Density 0.003%

    No Known Activations