© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 405
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions and processes involving crime, legality, and assistance

    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
    ulo
    -0.07
    agh
    -0.07
    ense
    -0.07
    rose
    -0.06
    ube
    -0.06
     Sle
    -0.06
    aba
    -0.06
    ara
    -0.06
    nett
    -0.06
    avar
    -0.06
    POSITIVE LOGITS
    utherland
    0.08
    criptor
    0.07
    ).__
    0.07
     behalf
    0.07
    elts
    0.07
    amak
    0.07
    imitives
    0.06
    704
    0.06
     trÆ°á»Łng
    0.06
     these
    0.06
    Activations Density 0.022%

    No Known Activations