© 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. 61344
    Prev
    Next
    INDEX
    Explanations

    interactions involving conflict and tension among characters

    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
    ecta
    -0.09
    chyb
    -0.09
    agit
    -0.08
    istle
    -0.08
    andalone
    -0.08
    arehouse
    -0.08
    _RPC
    -0.08
    رÙĬÙĦ
    -0.08
    elay
    -0.07
     ilet
    -0.07
    POSITIVE LOGITS
    ult
    0.08
     then
    0.07
    ulti
    0.07
     eventually
    0.07
     ult
    0.07
     exc
    0.06
     ultimately
    0.06
     resort
    0.06
     immobil
    0.06
     locked
    0.06
    Activations Density 0.026%

    No Known Activations