© 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. 9-LLAMASCOPE-RES-131K
    6. 95544
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and phrases related to physical settings or objects

    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
    Ñģлов
    -0.07
     Bret
    -0.06
    ija
    -0.06
    anford
    -0.06
    633
    -0.06
    677
    -0.06
    Ìĥ
    -0.06
    258
    -0.06
    742
    -0.06
    ména
    -0.06
    POSITIVE LOGITS
    VertexArray
    0.07
    rotch
    0.07
    apolis
    0.06
    undle
    0.06
    -pills
    0.06
    errupt
    0.06
    afen
    0.06
     Reeves
    0.06
     mob
    0.06
    ampoline
    0.06
    Activations Density 0.056%

    No Known Activations