© 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. 125057
    Prev
    Next
    INDEX
    Explanations

    phrases introducing answers or conclusions to questions

    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
    done
    -0.07
    ester
    -0.07
    istributed
    -0.07
    Done
    -0.06
    lip
    -0.06
    esters
    -0.06
    oes
    -0.06
    ÙĬÙĩ
    -0.06
    illis
    -0.06
    aura
    -0.06
    POSITIVE LOGITS
    948
    0.06
    woord
    0.06
    antt
    0.06
    ãĢĢãĥİ
    0.06
    wallet
    0.06
    ãĥķãĥ¬
    0.06
    (answer
    0.06
    .fm
    0.06
    947
    0.06
    ition
    0.06
    Activations Density 0.008%

    No Known Activations