© 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. 57212
    Prev
    Next
    INDEX
    Explanations

    references to cushions and cushioning materials

    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
    orial
    -0.07
    atts
    -0.07
    ifice
    -0.07
    zl
    -0.07
    strand
    -0.07
     Pazar
    -0.07
    nem
    -0.06
    agli
    -0.06
    лиÑĩ
    -0.06
    acific
    -0.06
    POSITIVE LOGITS
    edImage
    0.11
    edReader
    0.09
    ed
    0.08
    ette
    0.07
    less
    0.07
    ings
    0.07
    edin
    0.06
    mere
    0.06
    (es
    0.06
    edList
    0.06
    Activations Density 0.004%

    No Known Activations