© 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. 15-LLAMASCOPE-RES-131K
    11. 26802
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and places

    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
    eki
    -0.07
    ubern
    -0.07
    etcode
    -0.07
    çłĶ究æīĢ
    -0.07
    Squared
    -0.06
    ApiController
    -0.06
     Respect
    -0.06
    Ïħγ
    -0.06
    abcdefghijklmnop
    -0.06
    áp
    -0.06
    POSITIVE LOGITS
    agal
    0.08
    ulo
    0.06
     Merlin
    0.06
    âĦ¢
    0.06
    ify
    0.06
    _SCL
    0.06
    797
    0.06
    uli
    0.06
     bab
    0.06
    ul
    0.06
    Activations Density 0.021%

    No Known Activations