© 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 EvalsExportsinterp-engineNEWAPI 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. 2092
    Prev
    Next
    INDEX
    Explanations

    instances of words indicating acquisition or contact

    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
    InstanceOf
    -0.07
    eling
    -0.07
    aeda
    -0.06
    kich
    -0.06
    apon
    -0.06
    Destructor
    -0.06
    AtA
    -0.06
    .appendTo
    -0.06
    anki
    -0.06
    /tos
    -0.06
    POSITIVE LOGITS
     Holder
    0.07
     somehow
    0.06
    ernal
    0.06
    ovny
    0.06
     external
    0.06
    692
    0.06
    äng
    0.06
     extern
    0.06
     cuckold
    0.06
     rid
    0.06
    Activations Density 0.036%

    No Known Activations