© 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. 105994
    Prev
    Next
    INDEX
    Explanations

    intimate physical interactions and expressions of desire

    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
    roid
    -0.07
     Shr
    -0.06
    ough
    -0.06
    eyin
    -0.06
    lon
    -0.06
    obar
    -0.06
     Sweat
    -0.06
    orman
    -0.06
    iff
    -0.06
    rap
    -0.06
    POSITIVE LOGITS
     heat
    0.07
    ãĥ³ãĥĸ
    0.06
    _acquire
    0.06
     aft
    0.06
    nof
    0.06
     Pant
    0.06
     derecho
    0.06
    hots
    0.06
     sed
    0.06
    =end
    0.06
    Activations Density 0.014%

    No Known Activations