© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83905
    Prev
    Next
    INDEX
    Explanations

    technical jargon or identifiers related to telecommunications and communication protocols

    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
     GOODMAN
    -0.08
    ιά
    -0.07
    uos
    -0.07
    imple
    -0.06
    ç´Ķ
    -0.06
    (rd
    -0.06
    ymax
    -0.06
     Caldwell
    -0.06
    ucumber
    -0.06
    myfile
    -0.06
    POSITIVE LOGITS
     category
    0.07
     Category
    0.07
     verbs
    0.07
     sub
    0.07
     codes
    0.07
     subclass
    0.06
    acades
    0.06
    âĸį
    0.06
    _exempt
    0.06
     subclasses
    0.06
    Activations Density 0.007%

    No Known Activations