© 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. 87355
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns related to locations, events, and unique identifiers

    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
     Duy
    -0.07
    anny
    -0.07
    ecast
    -0.06
    erdale
    -0.06
    proc
    -0.06
    bsd
    -0.06
    berger
    -0.06
    ium
    -0.06
    drs
    -0.06
    _ORD
    -0.06
    POSITIVE LOGITS
     travel
    0.07
    æĹıèĩªæ²»
    0.07
     Gay
    0.06
    ETCH
    0.06
    _travel
    0.06
    .travel
    0.06
    erken
    0.06
    Gay
    0.06
    kate
    0.06
    asher
    0.06
    Activations Density 0.016%

    No Known Activations