© 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. 129058
    Prev
    Next
    INDEX
    Explanations

    concepts related to game mechanics and player objectives

    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
    _salt
    -0.08
    positor
    -0.06
    845
    -0.06
    éļĨ
    -0.06
    710
    -0.06
    agher
    -0.06
    ubit
    -0.06
    .absolute
    -0.06
    ecko
    -0.06
    ÑĢан
    -0.06
    POSITIVE LOGITS
     Bond
    0.07
    Bond
    0.07
     escapes
    0.07
     Bonds
    0.07
     escape
    0.06
    asure
    0.06
     civ
    0.06
     EXIT
    0.06
     trapped
    0.06
    asz
    0.06
    Activations Density 0.000%

    No Known Activations