© 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. 129033
    Prev
    Next
    INDEX
    Explanations

    intensifiers or amplifiers that modify the strength of adjectives and adverbs

    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
    kir
    -0.07
    ries
    -0.07
    dio
    -0.06
    igos
    -0.06
    777
    -0.06
    ÅĻÃŃm
    -0.06
    arme
    -0.06
    кин
    -0.06
    aln
    -0.06
    unny
    -0.06
    POSITIVE LOGITS
    ãģĹãģı
    0.07
    ucas
    0.07
    396
    0.07
    omen
    0.07
    ommen
    0.06
    ÅĦst
    0.06
    лиз
    0.06
    343
    0.06
     Kurul
    0.06
    asionally
    0.06
    Activations Density 0.048%

    No Known Activations