© 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. 17418
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "climb."

    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
     clue
    -0.07
    WARD
    -0.07
    gmt
    -0.06
    ivant
    -0.06
    imits
    -0.06
     Ames
    -0.06
    935
    -0.06
    oice
    -0.06
    opers
    -0.06
    vik
    -0.06
    POSITIVE LOGITS
    kil
    0.07
     Gon
    0.07
     onto
    0.07
     stairs
    0.06
    AZY
    0.06
    _mD
    0.06
    urr
    0.06
    erset
    0.06
    joy
    0.06
    empo
    0.06
    Activations Density 0.007%

    No Known Activations