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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126716
    Prev
    Next
    INDEX
    Explanations

    compound or complex nouns and phrases

    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
    emes
    -0.06
    posables
    -0.06
    hol
    -0.06
    grav
    -0.06
    /crypto
    -0.06
    ables
    -0.06
    kening
    -0.06
    amon
    -0.06
     Abel
    -0.06
    eman
    -0.06
    POSITIVE LOGITS
    -like
    0.15
    èά
    0.13
    -shaped
    0.12
    -esque
    0.11
    å¼ı
    0.10
    -style
    0.10
    -type
    0.10
    -sized
    0.09
    like
    0.09
     sized
    0.09
    Activations Density 0.048%

    No Known Activations