© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 105724
    Prev
    Next
    INDEX
    Explanations

    critical or significant nouns and verbs in various 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
    'gc
    -0.07
    -www
    -0.07
    -inner
    -0.07
    _HINT
    -0.07
    æľ
    -0.07
    aravel
    -0.07
    unitOfWork
    -0.07
    spy
    -0.07
    yaw
    -0.07
    dech
    -0.06
    POSITIVE LOGITS
    isme
    0.06
    itta
    0.06
    fold
    0.06
    inka
    0.06
     zij
    0.05
    ãĥªãĤ¢
    0.05
    áng
    0.05
    longleftrightarrow
    0.05
    137
    0.05
     imm
    0.05
    Activations Density 0.000%

    No Known Activations