© 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. 55512
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "P" or words beginning with "P"

    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
    age
    -0.07
    un
    -0.06
    ØŃ
    -0.06
    orda
    -0.06
    arching
    -0.06
    alim
    -0.06
    al
    -0.06
     hookers
    -0.06
    Y
    -0.06
    graded
    -0.05
    POSITIVE LOGITS
    üzel
    0.07
    elon
    0.07
    UINT
    0.07
    chter
    0.07
    iston
    0.07
    ادگÛĮ
    0.07
    BÃłi
    0.07
     phá»ij
    0.07
    allen
    0.07
    ptest
    0.07
    Activations Density 0.019%

    No Known Activations