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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106006
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cod" and its variations, indicating references to coding or codification

    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
    yb
    -0.08
    ees
    -0.07
    kees
    -0.07
    tfoot
    -0.07
    oire
    -0.06
    kle
    -0.06
    edm
    -0.06
    editable
    -0.06
    éī
    -0.06
    odb
    -0.06
    POSITIVE LOGITS
    pend
    0.11
    ding
    0.07
    ceed
    0.07
    cem
    0.07
    lymp
    0.07
    ovit
    0.07
    yssey
    0.07
    ious
    0.07
    ders
    0.07
    ded
    0.06
    Activations Density 0.012%

    No Known Activations