© 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. 16212
    Prev
    Next
    INDEX
    Explanations

    terms associated with visual impairment and vision-related concepts

    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
    ional
    -0.07
    виÑī
    -0.07
     edil
    -0.07
    ull
    -0.07
    icha
    -0.06
    leta
    -0.06
    .binding
    -0.06
    (es
    -0.06
    baum
    -0.06
    ut
    -0.06
    POSITIVE LOGITS
    aries
    0.08
    ight
    0.08
    Eye
    0.08
     Eye
    0.07
    úi
    0.07
    -eye
    0.07
     Sight
    0.07
    eye
    0.07
    eyes
    0.07
    furt
    0.07
    Activations Density 0.008%

    No Known Activations