© 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. 15-LLAMASCOPE-RES-131K
    11. 90065
    Prev
    Next
    INDEX
    Explanations

    code patterns related to string manipulation in programming

    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
    essel
    -0.07
    orgh
    -0.06
    fu
    -0.06
    ewolf
    -0.06
    zk
    -0.06
    ór
    -0.06
     Sala
    -0.06
    .Dom
    -0.06
     Carnegie
    -0.06
    ooth
    -0.06
    POSITIVE LOGITS
    »
    0.07
    bard
    0.07
    Overrides
    0.07
    ÙĤÙĬ
    0.06
     extr
    0.06
    ummer
    0.06
    anean
    0.06
    HQ
    0.06
    othy
    0.06
    aggregate
    0.06
    Activations Density 0.013%

    No Known Activations