© 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. 125126
    Prev
    Next
    INDEX
    Explanations

    references to collaborative contributions and projects

    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
    chk
    -0.07
    ouble
    -0.07
    oub
    -0.07
    chwitz
    -0.07
    essor
    -0.07
    dit
    -0.07
    PÅĻed
    -0.06
    ulton
    -0.06
    isos
    -0.06
    owe
    -0.06
    POSITIVE LOGITS
     via
    0.08
    andi
    0.06
    idi
    0.06
    ets
    0.06
    овж
    0.06
    upal
    0.06
    .azure
    0.06
    #a
    0.05
    ropa
    0.05
    .asp
    0.05
    Activations Density 0.048%

    No Known Activations