© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106227
    Prev
    Next
    INDEX
    Explanations

    instructions or objectives related to solving puzzles

    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
    etur
    -0.07
    ewire
    -0.07
    ushima
    -0.06
    ITERAL
    -0.06
    indow
    -0.06
    /met
    -0.06
    eyh
    -0.06
    RITE
    -0.06
    inka
    -0.06
     æ©Ł
    -0.06
    POSITIVE LOGITS
     undo
    0.07
     optionally
    0.06
     redis
    0.06
    zu
    0.06
    mpz
    0.06
    Ñıж
    0.06
    zac
    0.06
    ãĥ©ãĥĥãĤ¯
    0.06
    arts
    0.06
     playing
    0.06
    Activations Density 0.001%

    No Known Activations