© 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. 3627
    Prev
    Next
    INDEX
    Explanations

    references to the character Dexter Morgan and attributes related to his actions and moral complexities

    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
     Carrier
    -0.08
    stub
    -0.07
    carrier
    -0.07
    ffset
    -0.07
    Carrier
    -0.07
     granddaughter
    -0.07
    _dirty
    -0.07
    Ìĥ
    -0.06
     carrier
    -0.06
     carriers
    -0.06
    POSITIVE LOGITS
     serial
    0.10
     stalking
    0.08
     Serial
    0.08
    serial
    0.08
    Serial
    0.07
     stalk
    0.07
     cov
    0.06
    .serial
    0.06
     vigil
    0.06
    obs
    0.06
    Activations Density 0.002%

    No Known Activations