© 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. 3314
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and geographic locations

    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
     Shel
    -0.06
    }elseif
    -0.06
    ä¹ĥ
    -0.06
    &e
    -0.06
    lee
    -0.06
    ids
    -0.06
    peg
    -0.06
    貨
    -0.06
    rech
    -0.06
    preg
    -0.06
    POSITIVE LOGITS
     died
    0.10
     death
    0.09
     alive
    0.08
     اÙĦÙĪÙģ
    0.08
     endregion
    0.07
    anja
    0.07
     dies
    0.07
    deaux
    0.07
    -death
    0.07
    awai
    0.07
    Activations Density 0.002%

    No Known Activations