© 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. 16265
    Prev
    Next
    INDEX
    Explanations

    instances of variable declarations in code

    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
    ubber
    -0.07
    ayah
    -0.07
    bage
    -0.07
    indr
    -0.07
    apol
    -0.07
    ifestyles
    -0.07
    ayas
    -0.07
     киÑĪ
    -0.06
    ahlen
    -0.06
    edd
    -0.06
    POSITIVE LOGITS
     arr
    0.06
    itzer
    0.06
     Burgess
    0.06
    UrlParser
    0.06
     Signature
    0.06
     mens
    0.05
     nan
    0.05
    ê±°ëŀĺê°Ģ
    0.05
     Alger
    0.05
    OCI
    0.05
    Activations Density 0.000%

    No Known Activations