© 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. 9-LLAMASCOPE-RES-131K
    11. 95488
    Prev
    Next
    INDEX
    Explanations

    mentions of character exploits and adventures in narratives

    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
    zilla
    -0.07
    obraz
    -0.07
    annel
    -0.07
    ãĥĨãĥ«
    -0.07
    uele
    -0.07
    opi
    -0.07
    ovo
    -0.07
    atrice
    -0.07
    atori
    -0.07
    ska
    -0.07
    POSITIVE LOGITS
    ogl
    0.07
    eson
    0.07
    _tabs
    0.07
    ·»
    0.06
    endant
    0.06
    991
    0.06
    ĮĢ
    0.06
    義
    0.06
    ion
    0.06
     Prosecutor
    0.06
    Activations Density 0.020%

    No Known Activations