© 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. 17-LLAMASCOPE-RES-131K
    11. 3269
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names related to personal identities and relationships

    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
    eldon
    -0.08
    WR
    -0.07
    ofi
    -0.07
    curity
    -0.07
    raç
    -0.07
     bout
    -0.07
    eldo
    -0.06
    kup
    -0.06
    mÄĽ
    -0.06
    eka
    -0.06
    POSITIVE LOGITS
    -turned
    0.07
    ensis
    0.07
    ovna
    0.06
    ANNOT
    0.06
    wand
    0.06
    ená
    0.06
    گار
    0.06
    LOUD
    0.06
    ħn
    0.06
     BA
    0.06
    Activations Density 0.040%

    No Known Activations