© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 62347
    Prev
    Next
    INDEX
    Explanations

    narrative elements and key moments 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
    sein
    -0.07
    \base
    -0.07
    _cast
    -0.07
    quez
    -0.07
     DEALINGS
    -0.06
    adesh
    -0.06
    ouro
    -0.06
    NameValuePair
    -0.06
    unga
    -0.06
    allas
    -0.06
    POSITIVE LOGITS
     tehdy
    0.07
    ilk
    0.06
    ("'"
    0.06
     ÑĩÑĥж
    0.06
     she
    0.06
    CORD
    0.06
    font
    0.06
     kabil
    0.06
    ẹn
    0.05
    ä»ĵ
    0.05
    Activations Density 0.014%

    No Known Activations