© 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 EvalsExportsinterp-engineNEWAPI 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. 2401
    Prev
    Next
    INDEX
    Explanations

    instances of words related to selection and choice

    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
    ivol
    -0.07
    okt
    -0.06
    antino
    -0.06
    utherford
    -0.06
     Philosoph
    -0.06
    ulp
    -0.06
    kich
    -0.06
    oins
    -0.06
    mh
    -0.06
    æ¡£
    -0.06
    POSITIVE LOGITS
    acon
    0.08
    844
    0.07
    sworth
    0.07
     Rounds
    0.07
    urr
    0.07
    816
    0.07
    abeth
    0.06
    cona
    0.06
    amac
    0.06
     CHANNEL
    0.06
    Activations Density 0.001%

    No Known Activations