© 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. 106759
    Prev
    Next
    INDEX
    Explanations

    references to bookmarking or save features in the text

    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
     Thor
    -0.06
     Gentle
    -0.06
     rel
    -0.06
     reg
    -0.05
     gradually
    -0.05
     em
    -0.05
     red
    -0.05
    opor
    -0.05
    asket
    -0.05
    ainted
    -0.05
    POSITIVE LOGITS
    دÙĩ
    0.09
     uncert
    0.08
    dit
    0.07
    teki
    0.07
    'gc
    0.07
     Erotik
    0.07
    rame
    0.07
    ITHER
    0.07
    lil
    0.07
    times
    0.07
    Activations Density 0.001%

    No Known Activations