Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43996
    Prev
    Next
    INDEX
    Explanations

    instances of words related to "app."

    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
     Econ
    -0.07
    ting
    -0.07
    ek
    -0.07
    lm
    -0.07
    egal
    -0.07
     louis
    -0.07
    oler
    -0.07
    å·
    -0.06
     McL
    -0.06
    egin
    -0.06
    POSITIVE LOGITS
    elijke
    0.17
    elijk
    0.14
    lijke
    0.10
    ellij
    0.09
    aque
    0.09
    ÙĬÙĦÙĬ
    0.07
    илÑı
    0.07
    weg
    0.07
    ige
    0.07
    ische
    0.07
    Activations Density 0.001%

    No Known Activations