© 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. 15-LLAMASCOPE-RES-131K
    11. 61779
    Prev
    Next
    INDEX
    Explanations

    information related to physical attributes and statistics of individuals

    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
    ield
    -0.07
    ninger
    -0.07
     Dalton
    -0.07
    _macros
    -0.07
    outil
    -0.07
    çļĦæĥħ
    -0.07
    اش
    -0.07
     Associated
    -0.07
    erot
    -0.07
    opes
    -0.06
    POSITIVE LOGITS
    azu
    0.06
     suche
    0.06
     dere
    0.06
    aja
    0.06
    ùi
    0.06
    ilt
    0.05
    chin
    0.05
     Leap
    0.05
    aged
    0.05
    ilit
    0.05
    Activations Density 0.009%

    No Known Activations