© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106214
    Prev
    Next
    INDEX
    Explanations

    concepts related to existential threats and crises

    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
    inalg
    -0.08
    iena
    -0.07
    LBL
    -0.07
    %A
    -0.07
     VÅ¡
    -0.07
    .grpc
    -0.06
    że
    -0.06
    blade
    -0.06
    à¸²à¸ľ
    -0.06
    ?>>
    -0.06
    POSITIVE LOGITS
    èį
    0.06
    onga
    0.06
    wing
    0.06
    inherits
    0.06
    eree
    0.06
    omy
    0.06
     inheritance
    0.06
    aden
    0.06
    ane
    0.06
    istory
    0.06
    Activations Density 0.059%

    No Known Activations