© 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. 17-LLAMASCOPE-RES-131K
    11. 3417
    Prev
    Next
    INDEX
    Explanations

    narratives related to gardening and familial connections

    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
    vo
    -0.07
    zych
    -0.06
    ib
    -0.06
    elly
    -0.06
     itself
    -0.06
    Ñİн
    -0.06
    ReuseIdentifier
    -0.06
    ÑĬ
    -0.06
    ape
    -0.06
    bay
    -0.06
    POSITIVE LOGITS
    ctrine
    0.07
    itis
    0.07
    cord
    0.07
     trÃŃ
    0.06
    .ActionListener
    0.06
    848
    0.06
    .eclipse
    0.06
    .Annotations
    0.06
    anker
    0.06
    Annotation
    0.06
    Activations Density 0.003%

    No Known Activations