© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57130
    Prev
    Next
    INDEX
    Explanations

    programming language constructs related to variable and data type definitions

    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
    _finalize
    -0.08
    WithOptions
    -0.08
    grily
    -0.07
    arken
    -0.07
    ABCDEFGHI
    -0.07
    iddy
    -0.07
    croft
    -0.07
    etten
    -0.07
    elles
    -0.07
     LIABLE
    -0.07
    POSITIVE LOGITS
     PROGMEM
    0.10
     default
    0.08
    default
    0.07
     serialVersionUID
    0.06
     Default
    0.06
    ource
    0.06
    _default
    0.06
     fully
    0.06
    tbl
    0.06
    []
    0.05
    Activations Density 0.023%

    No Known Activations