© 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. 87346
    Prev
    Next
    INDEX
    Explanations

    references to physical interactions and closeness in relationships

    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
    iaux
    -0.07
     covers
    -0.06
     futures
    -0.06
    udu
    -0.06
    azzi
    -0.06
    æ¾
    -0.06
     DISP
    -0.06
    ucer
    -0.06
    pow
    -0.06
    Pow
    -0.06
    POSITIVE LOGITS
    _DEPRECATED
    0.07
    lige
    0.06
    nEnter
    0.06
    ect
    0.06
    912
    0.06
    ekt
    0.06
    ecycle
    0.06
    ìķħ
    0.06
    lander
    0.06
    Ïĥο
    0.06
    Activations Density 0.010%

    No Known Activations