© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 69809
    Prev
    Next
    INDEX
    Explanations

    conditional and hypothetical phrases related to possibilities or outcomes

    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
    ult
    -0.09
    con
    -0.07
    agh
    -0.06
    ht
    -0.06
     ultimate
    -0.06
    el
    -0.06
    Caps
    -0.06
    ault
    -0.06
    ated
    -0.06
    ACCESS
    -0.06
    POSITIVE LOGITS
     Sesso
    0.08
    anism
    0.08
    ented
    0.07
    ymax
    0.07
    aversable
    0.07
    exao
    0.07
    swers
    0.07
    ÑĢÑı
    0.07
    ابÙĤÙĩ
    0.07
    .bunifuFlatButton
    0.07
    Activations Density 0.005%

    No Known Activations