© 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. 76904
    Prev
    Next
    INDEX
    Explanations

    programmatic structures related to error handling and logging

    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
    ensch
    -0.08
    berger
    -0.07
    idot
    -0.07
    MeasureSpec
    -0.07
    íı°
    -0.07
    Absent
    -0.06
    Ñĥка
    -0.06
    SizeMode
    -0.06
    _deinit
    -0.06
    DOT
    -0.06
    POSITIVE LOGITS
    .printStackTrace
    0.09
    elen
    0.07
    ves
    0.07
    rrha
    0.06
    ror
    0.06
    StackTrace
    0.06
    717
    0.06
    rowable
    0.06
     perror
    0.06
    hend
    0.06
    Activations Density 0.020%

    No Known Activations