© 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. 61766
    Prev
    Next
    INDEX
    Explanations

    instances of the word "overlooked" and related terms indicating neglect or absence of attention

    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
    geber
    -0.07
    алÑİ
    -0.07
    ergus
    -0.07
    ¶Į
    -0.07
    cess
    -0.06
    ifu
    -0.06
    мага
    -0.06
    ronic
    -0.06
    ially
    -0.06
     вк
    -0.06
    POSITIVE LOGITS
    odel
    0.07
    SED
    0.07
    uster
    0.07
    ingly
    0.07
    /address
    0.06
    æİī
    0.06
     overlooked
    0.06
    ÏĥÏĦο
    0.06
     consideration
    0.06
     opportunities
    0.06
    Activations Density 0.005%

    No Known Activations