© 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. 126906
    Prev
    Next
    INDEX
    Explanations

    occurrences of variable declarations or assignments in a programming 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
    sic
    -0.08
    ErrorMsg
    -0.07
    ResponseStatus
    -0.07
    åĻ
    -0.07
    aż
    -0.07
    ίδα
    -0.07
    asje
    -0.07
    uye
    -0.07
    رسÛĮ
    -0.07
    .ie
    -0.07
    POSITIVE LOGITS
    izen
    0.07
    arg
    0.07
    umba
    0.07
    ether
    0.06
    umb
    0.06
    è«ĸ
    0.06
    UNDLE
    0.05
    ork
    0.05
    idy
    0.05
    IVE
    0.05
    Activations Density 0.005%

    No Known Activations