© 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. 71580
    Prev
    Next
    INDEX
    Explanations

    words associated with creative art and media production

    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
    Ìģt
    -0.07
    resse
    -0.07
     /*č↵
    -0.07
    à¥ĭà¤Ĥ,
    -0.07
     tük
    -0.07
     /**č↵
    -0.07
    borough
    -0.07
    едÑĮ
    -0.06
    ÑĢазд
    -0.06
    eri
    -0.06
    POSITIVE LOGITS
    /etc
    0.23
     etc
    0.14
    etc
    0.12
     combo
    0.10
     combination
    0.09
     combos
    0.09
     hybrid
    0.08
    ratio
    0.07
     whatever
    0.07
     combinations
    0.07
    Activations Density 0.086%

    No Known Activations