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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5739
    Prev
    Next
    INDEX
    Explanations

    concepts related to creativity and artistic expression

    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
    icer
    -0.08
    oun
    -0.07
    wards
    -0.07
    izio
    -0.07
    awning
    -0.07
    оÑģÑĤаÑĤ
    -0.07
    oup
    -0.06
    ept
    -0.06
    orman
    -0.06
    ln
    -0.06
    POSITIVE LOGITS
     into
    0.15
     forth
    0.13
     Into
    0.12
    Into
    0.11
    ToFront
    0.11
    into
    0.11
     onto
    0.11
     alive
    0.10
     together
    0.10
     INTO
    0.09
    Activations Density 0.027%

    No Known Activations