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

    Neuronpedia

    Jacobian LensNEW
    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. 130505
    Prev
    Next
    INDEX
    Explanations

    references to successors and succession-related terms

    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
    SEG
    -0.07
    alnız
    -0.06
    zelf
    -0.06
    jišť
    -0.06
    epar
    -0.06
    grave
    -0.06
    auss
    -0.06
    anton
    -0.06
    uien
    -0.06
    esian
    -0.06
    POSITIVE LOGITS
    ively
    0.13
    ship
    0.08
    물ìĿĦ
    0.08
    ivet
    0.07
    unce
    0.07
    ably
    0.07
     generations
    0.07
    entially
    0.07
    .Generation
    0.07
    daÅŁ
    0.07
    Activations Density 0.005%

    No Known Activations