© 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. 90035
    Prev
    Next
    INDEX
    Explanations

    relationships and personal connections between characters

    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
    _Tis
    -0.09
    #
    -0.08
    senal
    -0.08
    _mE
    -0.08
    andes
    -0.07
    idar
    -0.07
    395
    -0.07
    esiz
    -0.07
    elon
    -0.07
    hetto
    -0.07
    POSITIVE LOGITS
     his
    0.14
     himself
    0.11
    his
    0.10
    ä»ĸçļĦ
    0.09
     His
    0.08
     other
    0.08
     zijn
    0.07
     seu
    0.07
     seinen
    0.07
     another
    0.07
    Activations Density 0.034%

    No Known Activations