© 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. 3906
    Prev
    Next
    INDEX
    Explanations

    instances of abstract concepts or ideas

    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
    ÅĻev
    -0.07
    chten
    -0.07
     acomp
    -0.07
     ><?
    -0.07
    @js
    -0.07
    LN
    -0.07
    :variables
    -0.07
    à¥ģà¤Ł
    -0.06
    leftright
    -0.06
    Ñıв
    -0.06
    POSITIVE LOGITS
     maybe
    0.07
    aldi
    0.06
     potentially
    0.06
    adi
    0.06
    arily
    0.06
    òi
    0.06
     possibly
    0.05
    554
    0.05
     fucking
    0.05
     ident
    0.05
    Activations Density 0.000%

    No Known Activations