© 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. 106775
    Prev
    Next
    INDEX
    Explanations

    actions related to the selection and appointment of leadership positions

    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
    oon
    -0.07
     quý
    -0.06
    emes
    -0.06
    addtogroup
    -0.06
    _nsec
    -0.06
    ook
    -0.06
    onen
    -0.06
    머ëĭĪ
    -0.06
    amar
    -0.06
    ìłij
    -0.06
    POSITIVE LOGITS
     replacement
    0.13
     Replacement
    0.10
     replacements
    0.09
    replacement
    0.09
    ade
    0.09
     replace
    0.08
     replacing
    0.08
     someone
    0.08
     permanent
    0.08
     successor
    0.08
    Activations Density 0.014%

    No Known Activations