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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78573
    Prev
    Next
    INDEX
    Explanations

    statements related to changes in regulations or policies

    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
     svens
    -0.08
    aron
    -0.07
    Fcn
    -0.06
     Ãĸn
    -0.06
    okane
    -0.06
    ya
    -0.06
     longer
    -0.06
    enton
    -0.06
     meanwhile
    -0.05
    cdn
    -0.05
    POSITIVE LOGITS
     applies
    0.08
    luet
    0.08
     apply
    0.08
    tees
    0.08
     effective
    0.07
    .LayoutStyle
    0.07
    isma
    0.07
     applicable
    0.07
    _apply
    0.07
    apply
    0.07
    Activations Density 0.030%

    No Known Activations