© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16605
    Prev
    Next
    INDEX
    Explanations

    actions related to theft and robbery

    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
    人æīį
    -0.07
    cket
    -0.06
    ought
    -0.06
    ģm
    -0.06
    nam
    -0.06
    ragment
    -0.06
    ground
    -0.06
     su
    -0.06
    zek
    -0.06
    unge
    -0.06
    POSITIVE LOGITS
    ivals
    0.08
    akte
    0.07
    rio
    0.07
     wealthy
    0.07
     stealing
    0.06
    ãģ¶
    0.06
     affluent
    0.06
     أجÙĦ
    0.06
    NSBundle
    0.06
    .getProperties
    0.06
    Activations Density 0.018%

    No Known Activations