© 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. 22-LLAMASCOPE-RES-131K
    11. 4304
    Prev
    Next
    INDEX
    Explanations

    instances of specific German nouns and terms related to geography and locations

    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
     dern
    -0.06
     Nad
    -0.06
    inho
    -0.06
    andler
    -0.06
    ioneer
    -0.06
    maz
    -0.06
     Hercules
    -0.06
     tur
    -0.06
     Shane
    -0.05
     chi
    -0.05
    POSITIVE LOGITS
     Norm
    0.16
    Norm
    0.13
     norm
    0.12
     Norman
    0.11
    norm
    0.11
    .norm
    0.10
     norms
    0.10
    _norm
    0.09
    (norm
    0.09
     ноÑĢм
    0.09
    Activations Density 0.010%

    No Known Activations