© 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. 82525
    Prev
    Next
    INDEX
    Explanations

    negative expressions and limitations regarding social interactions

    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
    eldon
    -0.07
    รม
    -0.07
    ären
    -0.07
    едж
    -0.06
    ieten
    -0.06
    _starts
    -0.06
    rana
    -0.06
    uhl
    -0.06
    ibble
    -0.06
    uger
    -0.06
    POSITIVE LOGITS
     outside
    0.09
     thÄĥm
    0.08
    Outside
    0.07
     exc
    0.07
    outside
    0.07
     Outside
    0.07
     visits
    0.07
    Ñĩки
    0.07
     gall
    0.06
     visit
    0.06
    Activations Density 0.025%

    No Known Activations