© 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. 3353
    Prev
    Next
    INDEX
    Explanations

    instances of personal memories being recalled

    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
    ching
    -0.07
    eldom
    -0.07
    ñana
    -0.06
    ic
    -0.06
    osi
    -0.06
    pering
    -0.06
    _Release
    -0.06
    orsche
    -0.06
    idding
    -0.06
    older
    -0.06
    POSITIVE LOGITS
     being
    0.13
     having
    0.10
    being
    0.09
     Being
    0.08
    Being
    0.08
     seeing
    0.07
    (ed
    0.07
    -being
    0.07
    被
    0.06
     particular
    0.06
    Activations Density 0.007%

    No Known Activations