© 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. 5-LLAMASCOPE-RES-131K
    6. 126452
    Prev
    Next
    INDEX
    Explanations

    phrases expressing comparisons or conditions

    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
    ogi
    -0.07
    shal
    -0.07
    ernet
    -0.07
    /Card
    -0.06
    天天
    -0.06
    AffineTransform
    -0.06
    merchant
    -0.06
    ensa
    -0.06
    imens
    -0.06
    opal
    -0.06
    POSITIVE LOGITS
    els
    0.07
    able
    0.07
     break
    0.06
    ELS
    0.06
    oria
    0.06
     Mag
    0.06
    lea
    0.06
     Kaw
    0.06
     Gro
    0.05
     bra
    0.05
    Activations Density 0.004%

    No Known Activations