© 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. 3305
    Prev
    Next
    INDEX
    Explanations

    words related to the importance or degree of impact in a given context

    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
    eka
    -0.07
    ãĤ¹ãĥĨ
    -0.07
    /OR
    -0.07
    zim
    -0.07
    imitive
    -0.07
    à¹ĥ
    -0.07
    idon
    -0.06
     hug
    -0.06
    victim
    -0.06
    ipa
    -0.06
    POSITIVE LOGITS
    _like
    0.07
    /modules
    0.06
    /logger
    0.06
    ëĭī
    0.06
     Gros
    0.06
    _PROM
    0.06
    -Origin
    0.06
    нÑĸÑĪ
    0.06
     ABD
    0.06
     é¹
    0.06
    Activations Density 0.001%

    No Known Activations