© 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 EvalsExportsinterp-engineNEWAPI 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. 95565
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Fam" and its variations, indicating a focus on familial themes or relationships

    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
    MEDIA
    -0.08
    aes
    -0.07
    ypse
    -0.07
    aepernick
    -0.07
    iber
    -0.07
     dob
    -0.07
    anson
    -0.06
    ت
    -0.06
    едеÑĢа
    -0.06
     Transit
    -0.06
    POSITIVE LOGITS
    bling
    0.09
    blem
    0.07
    uly
    0.07
    ouflage
    0.07
    yr
    0.07
     Winchester
    0.07
    rish
    0.07
     Sink
    0.07
    plit
    0.06
    fare
    0.06
    Activations Density 0.005%

    No Known Activations