© 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. 83093
    Prev
    Next
    INDEX
    Explanations

    references to the reader or audience

    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
    roups
    -0.07
    олÑı
    -0.07
     éģĵ
    -0.06
    iday
    -0.06
    erre
    -0.06
    andex
    -0.06
     ç©
    -0.06
    mise
    -0.06
    lope
    -0.06
    dna
    -0.06
    POSITIVE LOGITS
    enler
    0.07
    poses
    0.07
    urg
    0.07
    ±Ð¾ÑĤ
    0.06
    urette
    0.06
    GIN
    0.06
    /stdc
    0.06
    ABSPATH
    0.06
    vez
    0.06
    EqualityComparer
    0.06
    Activations Density 0.010%

    No Known Activations