© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76178
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols 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
    uell
    -0.07
    [section
    -0.06
    \model
    -0.06
    mmc
    -0.06
     Federation
    -0.06
    ìĥī
    -0.06
    abay
    -0.06
     norge
    -0.06
    762
    -0.06
    mai
    -0.06
    POSITIVE LOGITS
    hunter
    0.06
    owitz
    0.06
    rab
    0.06
    acons
    0.06
    ynch
    0.06
    apl
    0.06
    acias
    0.06
    tees
    0.06
    uids
    0.06
    Tw
    0.05
    Activations Density 0.055%

    No Known Activations