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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90540
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe actions or processes involving movement or manipulation

    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
    assin
    -0.06
    toi
    -0.06
    ech
    -0.06
    land
    -0.06
    ulp
    -0.06
    psc
    -0.06
    bk
    -0.05
    ↵↵
    -0.05
    lex
    -0.05
    ipping
    -0.05
    POSITIVE LOGITS
    å¹ķ
    0.07
    KHTML
    0.07
    omez
    0.07
    íĨłíĨł
    0.07
    ños
    0.07
    åĪļæīį
    0.07
    ÑģÑıг
    0.07
    URRED
    0.07
    ucceed
    0.07
    (Gravity
    0.07
    Activations Density 0.006%

    No Known Activations