© 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. 40131
    Prev
    Next
    INDEX
    Explanations

    strings that relate to Social Security identifiers and associated codes

    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
    ãĥ³ãĥĸ
    -0.07
    ammad
    -0.07
    pagen
    -0.07
    aurus
    -0.06
    ubi
    -0.06
    edition
    -0.06
    ÑĸÑģно
    -0.06
    ToWorld
    -0.06
    égor
    -0.06
    touches
    -0.06
    POSITIVE LOGITS
    mates
    0.08
    .usermodel
    0.07
    canf
    0.07
    rip
    0.07
    ssa
    0.07
    /ss
    0.07
    lingen
    0.06
    lined
    0.06
    linger
    0.06
    çŃĭ
    0.06
    Activations Density 0.015%

    No Known Activations