© 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. 126439
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and structural elements in the text

    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
     пеÑĢел
    -0.06
    .gf
    -0.06
    ascus
    -0.06
    anza
    -0.06
     McL
    -0.06
    .statusText
    -0.06
    á»Ĩ
    -0.05
     Ear
    -0.05
    locked
    -0.05
    argout
    -0.05
    POSITIVE LOGITS
    ¶Į
    0.07
    otton
    0.07
    aal
    0.07
    iani
    0.07
     Stokes
    0.07
     Fit
    0.07
    oller
    0.07
    357
    0.06
     fit
    0.06
    ersist
    0.06
    Activations Density 0.000%

    No Known Activations