© 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. 28785
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation, particularly periods and question marks

    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
    unga
    -0.07
    stants
    -0.07
    onya
    -0.07
    .nlm
    -0.07
     valueForKey
    -0.07
    bih
    -0.06
    egis
    -0.06
    /wiki
    -0.06
    udur
    -0.06
    elop
    -0.06
    POSITIVE LOGITS
     maybe
    0.08
     éĹ
    0.06
     fuck
    0.06
     Exceptions
    0.06
    inson
    0.06
     And
    0.06
    amo
    0.06
     Bu
    0.06
     Fuck
    0.06
     therefore
    0.06
    Activations Density 0.008%

    No Known Activations