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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 96216
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate consequences or blame

    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
    steen
    -0.07
    anuts
    -0.07
    ãĤ¦ãĤ©
    -0.07
    dash
    -0.07
     Dash
    -0.07
    523
    -0.07
    _YUV
    -0.07
    opoulos
    -0.07
    isher
    -0.07
    óz
    -0.07
    POSITIVE LOGITS
    alendar
    0.07
    igid
    0.06
     Brew
    0.06
     height
    0.06
    /tool
    0.05
    -bold
    0.05
     ÐŀлекÑģанд
    0.05
    umbnail
    0.05
    úc
    0.05
     SOS
    0.05
    Activations Density 0.006%

    No Known Activations