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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61836
    Prev
    Next
    INDEX
    Explanations

    words related to specific individuals' names

    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
    es
    -0.10
    estro
    -0.08
    edBy
    -0.07
    eenth
    -0.07
    ième
    -0.07
    ife
    -0.07
    .mb
    -0.07
    egan
    -0.07
    adows
    -0.06
    eva
    -0.06
    POSITIVE LOGITS
    ging
    0.09
    ged
    0.07
    ripp
    0.06
    gin
    0.06
    uet
    0.06
    æħİ
    0.06
    otto
    0.06
    jed
    0.06
    pec
    0.06
    rgan
    0.06
    Activations Density 0.040%

    No Known Activations