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

    Neuronpedia

    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. 74304
    Prev
    Next
    INDEX
    Explanations

    expressions of critique or analysis related to artistic works

    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
     a
    -0.06
    icone
    -0.06
     Nur
    -0.06
     Greater
    -0.06
    NotAllowed
    -0.06
    lament
    -0.06
     Joined
    -0.06
    êt
    -0.05
     deposit
    -0.05
    .rd
    -0.05
    POSITIVE LOGITS
     overall
    0.09
     everything
    0.09
    overall
    0.09
    ODO
    0.08
    everything
    0.08
    éné
    0.08
     tudo
    0.07
    ÐĴÐŀ
    0.07
    _TAC
    0.07
    organization
    0.07
    Activations Density 0.019%

    No Known Activations