Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96177
    Prev
    Next
    INDEX
    Explanations

    themes related to narrative, representation, and power dynamics in storytelling

    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
    _CMP
    -0.07
    ido
    -0.07
    ÑĬ
    -0.07
    baar
    -0.07
    ίο
    -0.07
    csi
    -0.07
    swire
    -0.06
    oru
    -0.06
    hei
    -0.06
    achen
    -0.06
    POSITIVE LOGITS
    obby
    0.07
     Paulo
    0.06
     Tyson
    0.06
     dew
    0.06
    892
    0.05
     Laurie
    0.05
    416
    0.05
     experienced
    0.05
    605
    0.05
    udeau
    0.05
    Activations Density 0.006%

    No Known Activations