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. 87496
    Prev
    Next
    INDEX
    Explanations

    distinct sources or references in a report-like context

    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
    öyle
    -0.08
    ADDE
    -0.07
    isel
    -0.07
    $MESS
    -0.07
    Scaler
    -0.07
     stead
    -0.07
    WithDuration
    -0.07
    ationToken
    -0.07
    ัà¸Ķ
    -0.06
    .setUp
    -0.06
    POSITIVE LOGITS
     cul
    0.06
    imar
    0.05
    obo
    0.05
    овÑĸд
    0.05
    ASA
    0.05
    cond
    0.05
    itar
    0.05
     cond
    0.05
    fos
    0.05
    ayah
    0.05
    Activations Density 0.004%

    No Known Activations