© 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. 3819
    Prev
    Next
    INDEX
    Explanations

    references to art and artistic quality

    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
     erotik
    -0.07
     :č↵
    -0.07
    å£
    -0.07
    _UNIFORM
    -0.07
    argin
    -0.07
    alama
    -0.07
    udio
    -0.07
    eÄį
    -0.07
     å£
    -0.06
     пÑĢед
    -0.06
    POSITIVE LOGITS
     &
    0.08
    lac
    0.07
     Battlefield
    0.06
    &t
    0.06
    ôn
    0.06
    ilig
    0.06
    emos
    0.06
     Hass
    0.06
    ujte
    0.06
    inely
    0.05
    Activations Density 0.052%

    No Known Activations