© 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. 71169
    Prev
    Next
    INDEX
    Explanations

    terms related to numerical or statistical data

    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
    krv
    -0.07
    å¢
    -0.07
     Klein
    -0.06
    áz
    -0.06
    ascus
    -0.06
    crm
    -0.06
    ossal
    -0.06
    czy
    -0.06
    TC
    -0.06
    esco
    -0.06
    POSITIVE LOGITS
    rone
    0.08
    бÑĥÑĤ
    0.07
    QRST
    0.07
    aga
    0.07
    conc
    0.07
    HEMA
    0.07
    hiba
    0.06
    ltk
    0.06
    ÑĨвеÑĤ
    0.06
     ActiveForm
    0.06
    Activations Density 0.019%

    No Known Activations