© 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. 83083
    Prev
    Next
    INDEX
    Explanations

    discussions related to care, assessments, and rights concerning individuals, particularly children

    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
    agner
    -0.06
    åħ»
    -0.06
    ollen
    -0.06
    ãģ«ãģ¦
    -0.06
    yen
    -0.06
     hoy
    -0.06
     Traverse
    -0.05
     characterization
    -0.05
    oy
    -0.05
     yet
    -0.05
    POSITIVE LOGITS
     particulars
    0.08
    .gs
    0.07
    uest
    0.07
    /people
    0.07
    orta
    0.07
    velt
    0.07
    _constants
    0.07
    getDrawable
    0.07
    .mapbox
    0.07
    atform
    0.06
    Activations Density 0.000%

    No Known Activations