© 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. 74807
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence-ending marks

    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
    код
    -0.07
    ¶Į
    -0.07
    dess
    -0.07
    ahat
    -0.07
    TOTYPE
    -0.07
     ÑĩиÑĤ
    -0.07
    гÑĥ
    -0.07
    ipsis
    -0.07
    aje
    -0.07
    lesia
    -0.07
    POSITIVE LOGITS
    ao
    0.06
    implify
    0.06
    orges
    0.06
    423
    0.06
    forth
    0.06
     Rue
    0.06
    ari
    0.06
    ieux
    0.06
    enschaft
    0.05
    ans
    0.05
    Activations Density 0.003%

    No Known Activations