© 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. 76866
    Prev
    Next
    INDEX
    Explanations

    elements related to television genres and formats

    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
    ruk
    -0.07
    swick
    -0.06
    emu
    -0.06
     titular
    -0.06
     Choices
    -0.06
     Handy
    -0.06
    slu
    -0.06
     marg
    -0.06
    ONUS
    -0.06
    keley
    -0.06
    POSITIVE LOGITS
    _TM
    0.07
    è³
    0.07
    yen
    0.07
    >null
    0.06
    acional
    0.06
    $$$$
    0.06
    ane
    0.06
    วà¸Ļ
    0.06
    omba
    0.06
    aton
    0.06
    Activations Density 0.023%

    No Known Activations