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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 43857
    Prev
    Next
    INDEX
    Explanations

    elements related to storytelling and fictional 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
    -desktop
    -0.07
    Geom
    -0.06
    è³Ģ
    -0.06
    edImage
    -0.06
    ,readonly
    -0.06
     hüküm
    -0.05
    뮤
    -0.05
     congrat
    -0.05
    ÑģÑĤÑĢи
    -0.05
    estyle
    -0.05
    POSITIVE LOGITS
     fodder
    0.16
     material
    0.15
     fertile
    0.14
    material
    0.12
     topics
    0.12
     subject
    0.12
     ripe
    0.12
     subjects
    0.12
     juicy
    0.11
     story
    0.11
    Activations Density 0.060%

    No Known Activations