© 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. 5-LLAMASCOPE-RES-131K
    11. 126537
    Prev
    Next
    INDEX
    Explanations

    references to transitions of possession or responsibility

    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
    bert
    -0.07
    uela
    -0.06
    abella
    -0.06
    oad
    -0.06
    urrection
    -0.06
    alls
    -0.06
     druž
    -0.06
    anka
    -0.06
    _misc
    -0.06
     pending
    -0.05
    POSITIVE LOGITS
    ìĤ¬ìĿ´
    0.08
    illard
    0.07
    iface
    0.07
    ascar
    0.07
    elu
    0.07
    voir
    0.06
    edor
    0.06
     Tavern
    0.06
    icket
    0.06
    concert
    0.06
    Activations Density 0.001%

    No Known Activations