© 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. 128726
    Prev
    Next
    INDEX
    Explanations

    positive and negative descriptors of experiences or feelings

    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
    .qq
    -0.07
    raphics
    -0.07
    essen
    -0.06
    inth
    -0.06
     aks
    -0.06
    aeda
    -0.06
    874
    -0.06
    ORM
    -0.06
    vox
    -0.06
    UZ
    -0.06
    POSITIVE LOGITS
    erson
    0.07
     personally
    0.07
    ETS
    0.07
     himself
    0.07
    istrovstvÃŃ
    0.07
    sky
    0.06
     credible
    0.06
     nett
    0.06
    yle
    0.06
    sville
    0.06
    Activations Density 0.019%

    No Known Activations