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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-LLAMASCOPE-RES-131K
    6. 5266
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of."

    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
    s
    -0.08
    formed
    -0.07
    eldom
    -0.06
    alls
    -0.06
    wy
    -0.06
    _ALIGNMENT
    -0.06
    adera
    -0.06
    rz
    -0.06
    нг
    -0.06
    alysis
    -0.06
    POSITIVE LOGITS
    icina
    0.08
    Äı
    0.07
    icers
    0.07
    itzer
    0.07
    ta
    0.07
    óż
    0.07
    gend
    0.07
    icer
    0.06
    oten
    0.06
    tit
    0.06
    Activations Density 0.004%

    No Known Activations