© 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. 71489
    Prev
    Next
    INDEX
    Explanations

    phrases and terms associated with maintenance, repair, and safety issues

    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
    .scalablytyped
    -0.07
    istring
    -0.07
    INVALID
    -0.07
    bero
    -0.06
     Dysfunction
    -0.06
    /inc
    -0.06
    _exception
    -0.06
     kariy
    -0.06
    á»ĭch
    -0.06
    ond
    -0.06
    POSITIVE LOGITS
     lack
    0.11
     too
    0.09
    lack
    0.09
     absence
    0.08
     Too
    0.08
    too
    0.08
     outright
    0.08
    Too
    0.08
     missing
    0.07
     sp
    0.07
    Activations Density 0.029%

    No Known Activations