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

    Neuronpedia

    Jacobian LensNEW
    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. 57378
    Prev
    Next
    INDEX
    Explanations

    references to films and elements associated with horror and low-budget genres

    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
    ucz
    -0.08
    (es
    -0.07
    nan
    -0.07
    884
    -0.07
     nét
    -0.07
    emma
    -0.06
    /--
    -0.06
    lfw
    -0.06
    lek
    -0.06
    ï¸ı
    -0.06
    POSITIVE LOGITS
    /simple
    0.08
    -level
    0.08
    weg
    0.08
    adoo
    0.08
    -style
    0.07
    (low
    0.07
    -grade
    0.07
    -type
    0.07
    arker
    0.07
    -priced
    0.07
    Activations Density 0.039%

    No Known Activations