© 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. 78136
    Prev
    Next
    INDEX
    Explanations

    variables and references related to application profiles in a coding context

    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
    lit
    -0.07
    ahun
    -0.07
    ç¿Ķ
    -0.07
    acio
    -0.07
    util
    -0.07
    ÑĢÑĥÑĤ
    -0.07
    rende
    -0.07
    esar
    -0.06
    és
    -0.06
    SpaceItem
    -0.06
    POSITIVE LOGITS
    -relative
    0.06
     Www
    0.06
    ynchronously
    0.06
     discriminator
    0.06
     Garc
    0.06
     Rev
    0.06
     createSelector
    0.06
    setId
    0.06
    ertiary
    0.06
    ssa
    0.06
    Activations Density 0.039%

    No Known Activations