© 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. 87215
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters commonly used in programming or coding contexts

    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
     ny
    -0.07
    ãĥĥãĥĦ
    -0.07
    coon
    -0.06
     Hampton
    -0.06
    ResourceId
    -0.06
    rk
    -0.06
    sembled
    -0.05
    .comm
    -0.05
    raison
    -0.05
     slova
    -0.05
    POSITIVE LOGITS
    ово
    0.06
    Ñĥнок
    0.06
    ENA
    0.06
    rev
    0.06
    Mus
    0.06
    akit
    0.06
    AGO
    0.06
    ago
    0.06
     ear
    0.06
    olo
    0.06
    Activations Density 0.029%

    No Known Activations