© 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. 15-LLAMASCOPE-RES-131K
    11. 89622
    Prev
    Next
    INDEX
    Explanations

    titles and roles of individuals in various contexts, particularly leadership positions

    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
    ahat
    -0.08
    ieber
    -0.07
    lernen
    -0.07
    ento
    -0.07
    ehr
    -0.06
     Hat
    -0.06
    Hat
    -0.06
    celik
    -0.06
     ($.
    -0.06
    emale
    -0.06
    POSITIVE LOGITS
    idos
    0.07
    ạ
    0.07
     higher
    0.07
    bows
    0.06
    ãĥĭãĥ¡
    0.06
    rete
    0.06
    ppers
    0.06
    tons
    0.06
    ÑĢÑĥн
    0.06
    gross
    0.06
    Activations Density 0.026%

    No Known Activations