© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 70513
    Prev
    Next
    INDEX
    Explanations

    phrases related to narrative structure or elements of 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
    ÑĢава
    -0.07
    quiries
    -0.07
    ertz
    -0.07
    ilt
    -0.07
    _THREADS
    -0.07
    akes
    -0.06
    ooke
    -0.06
    mons
    -0.06
    ombo
    -0.06
    acades
    -0.06
    POSITIVE LOGITS
    odb
    0.07
    ainless
    0.07
    slaught
    0.07
    ayah
    0.06
    feit
    0.06
    ìĶ©
    0.06
     unc
    0.06
    ebin
    0.06
    od
    0.06
    -toggler
    0.06
    Activations Density 0.266%

    No Known Activations