© 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. 77328
    Prev
    Next
    INDEX
    Explanations

    components of mathematical notation and formatting

    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
    uch
    -0.08
    apat
    -0.07
    haus
    -0.07
    oret
    -0.07
    oft
    -0.07
    ddy
    -0.07
    atorio
    -0.07
    æ¦ľ
    -0.06
     Angeles
    -0.06
    ÑĥÑĩа
    -0.06
    POSITIVE LOGITS
    ï¸
    0.09
    irror
    0.07
    uida
    0.07
    alice
    0.06
    ï¸ı
    0.06
    igkeit
    0.06
    (DataType
    0.06
    iglia
    0.06
    svc
    0.06
    ichick
    0.06
    Activations Density 0.022%

    No Known Activations