© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83952
    Prev
    Next
    INDEX
    Explanations

    words related to attraction or interest

    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
    ed
    -0.08
    uw
    -0.07
    ghi
    -0.07
     blind
    -0.07
    ely
    -0.06
     же
    -0.06
    gies
    -0.06
    å½¹
    -0.06
    utz
    -0.06
     Stephan
    -0.06
    POSITIVE LOGITS
    ance
    0.08
     appeal
    0.08
     Appeal
    0.08
     appeals
    0.08
    ingly
    0.08
     appealed
    0.07
    able
    0.07
    auce
    0.07
    ÅĽci
    0.07
    antly
    0.07
    Activations Density 0.006%

    No Known Activations