Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 106675
    Prev
    Next
    INDEX
    Explanations

    descriptive language that highlights beauty and aesthetics

    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
     hay
    -0.06
     manifest
    -0.06
    .Layer
    -0.06
     CIF
    -0.06
    assing
    -0.05
     Ott
    -0.05
    _firestore
    -0.05
     occult
    -0.05
     hardcore
    -0.05
    shaw
    -0.05
    POSITIVE LOGITS
     facilities
    0.09
     buildings
    0.09
     equipment
    0.09
     facility
    0.08
    facility
    0.08
     Facilities
    0.08
    pees
    0.07
    build
    0.07
     premises
    0.07
    è¨ŃåĤĻ
    0.07
    Activations Density 0.069%

    No Known Activations