© 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. 3211
    Prev
    Next
    INDEX
    Explanations

    phrases indicating tendencies or predispositions toward certain behaviors or characteristics

    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
     обол
    -0.07
     ÐŁÑĢа
    -0.07
    lsen
    -0.07
    arie
    -0.07
    arat
    -0.06
    aldi
    -0.06
    ItemImage
    -0.06
    ajs
    -0.06
    ìĹĨëĬĶ
    -0.06
    ni
    -0.06
    POSITIVE LOGITS
    heimer
    0.08
     violence
    0.07
    cox
    0.06
    addle
    0.06
    athers
    0.06
     Cox
    0.06
     toward
    0.06
    yne
    0.06
     Guy
    0.06
    SError
    0.06
    Activations Density 0.018%

    No Known Activations