© 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. 82774
    Prev
    Next
    INDEX
    Explanations

    specific adjectives and descriptors related to materials and conditions

    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
    idon
    -0.07
    Ñģли
    -0.07
    rray
    -0.07
    indre
    -0.07
    gal
    -0.07
    aces
    -0.07
     werk
    -0.06
    ìłķìĿĦ
    -0.06
    Gal
    -0.06
    teg
    -0.06
    POSITIVE LOGITS
     preferably
    0.09
     ones
    0.07
    prefer
    0.07
     enough
    0.06
    ä¸Ķ
    0.06
     nÃło
    0.06
    ummings
    0.06
    -нибÑĥдÑĮ
    0.06
    ichtig
    0.06
     aftermarket
    0.06
    Activations Density 0.037%

    No Known Activations