© 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. 83336
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names and surnames

    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
    çĦ¶
    -0.07
    ford
    -0.07
    ach
    -0.07
    tas
    -0.07
    iber
    -0.07
    combe
    -0.06
    ack
    -0.06
    ther
    -0.06
    Handled
    -0.06
    ar
    -0.06
    POSITIVE LOGITS
    (es
    0.10
    plorer
    0.09
    -vous
    0.08
    epam
    0.08
    es
    0.08
    elpers
    0.07
     latter
    0.07
    imoto
    0.07
    ifix
    0.07
    esModule
    0.07
    Activations Density 0.020%

    No Known Activations