© 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. 3934
    Prev
    Next
    INDEX
    Explanations

    instances of numbers and numeric phrases

    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
    маз
    -0.07
    lik
    -0.07
     homosex
    -0.06
     Ket
    -0.06
     discussion
    -0.06
    maal
    -0.06
     Stateless
    -0.06
     thôi
    -0.06
     Nack
    -0.06
    ä¾Ľ
    -0.06
    POSITIVE LOGITS
    dera
    0.07
    $MESS
    0.07
    elsius
    0.07
    BackingField
    0.06
    umin
    0.06
     employer
    0.06
    Vectorizer
    0.06
     mê
    0.06
     ymin
    0.06
    ertz
    0.06
    Activations Density 0.000%

    No Known Activations