© 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. 117261
    Prev
    Next
    INDEX
    Explanations

    words related to potential outcomes or influential factors

    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
    vinc
    -0.07
     amac
    -0.07
    .sd
    -0.07
    zeichnet
    -0.07
    _parms
    -0.06
    etim
    -0.06
     Chew
    -0.06
    Dean
    -0.06
    ignum
    -0.06
    adele
    -0.06
    POSITIVE LOGITS
     determining
    0.11
     determines
    0.11
     determine
    0.11
     factors
    0.10
     determin
    0.10
    Determin
    0.09
    å½±éŁ¿
    0.09
     influence
    0.09
    åĨ³å®ļ
    0.09
     affecting
    0.09
    Activations Density 0.037%

    No Known Activations