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. 60996
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "aus" and its variations in different contexts

    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
    isiert
    -0.08
    919
    -0.08
    веÑĢд
    -0.07
    Ñĩенко
    -0.07
    ãĤīãģĽ
    -0.07
    chten
    -0.07
    تÙĬÙĨ
    -0.07
    acades
    -0.06
    /DTD
    -0.06
    öh
    -0.06
    POSITIVE LOGITS
    IFE
    0.06
    ubb
    0.06
    ayla
    0.06
     Sud
    0.06
    -away
    0.06
    eya
    0.06
    Ñħи
    0.05
    natal
    0.05
    olon
    0.05
    away
    0.05
    Activations Density 0.005%

    No Known Activations