Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5299
    Prev
    Next
    INDEX
    Explanations

    references to fog or its related imagery

    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
    istrovstvÃŃ
    -0.07
    FRING
    -0.07
    icamente
    -0.07
    agoon
    -0.07
    iger
    -0.07
    UPLE
    -0.07
    lü
    -0.07
    šak
    -0.07
    stroy
    -0.06
    permanent
    -0.06
    POSITIVE LOGITS
    arty
    0.11
    ging
    0.09
    ged
    0.09
    gy
    0.08
    lio
    0.08
    ues
    0.08
    elson
    0.07
    iveness
    0.07
    adh
    0.06
    elman
    0.06
    Activations Density 0.003%

    No Known Activations