© 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. 82962
    Prev
    Next
    INDEX
    Explanations

    instances of identification or connections to criminal investigations

    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
    AccessType
    -0.08
    chal
    -0.08
    ighth
    -0.08
    claimer
    -0.07
     Toilet
    -0.07
    feld
    -0.07
    ckill
    -0.07
    tgl
    -0.07
    ItemCount
    -0.07
     COPYRIGHT
    -0.07
    POSITIVE LOGITS
     trace
    0.09
     matches
    0.09
     ident
    0.08
     identification
    0.08
     identity
    0.08
    trace
    0.08
     match
    0.08
     Match
    0.08
     DNA
    0.08
    -match
    0.08
    Activations Density 0.039%

    No Known Activations