© 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. 15-LLAMASCOPE-RES-131K
    11. 86539
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    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
     Tal
    -0.07
     recent
    -0.06
     accessor
    -0.06
     Morm
    -0.06
    ixin
    -0.05
    bic
    -0.05
    rouch
    -0.05
     sole
    -0.05
     ext
    -0.05
     Ner
    -0.05
    POSITIVE LOGITS
    ãĥ¼ãĥį
    0.08
     (!((
    0.08
    okie
    0.07
    нам
    0.07
    summ
    0.07
    apist
    0.07
    ledon
    0.07
    enty
    0.07
    awei
    0.07
    acl
    0.07
    Activations Density 0.000%

    No Known Activations