© 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. 17-LLAMASCOPE-RES-131K
    6. 107202
    Prev
    Next
    INDEX
    Explanations

    syntactic patterns involving punctuation and sentence structures

    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
    acher
    -0.07
    راÙĨ
    -0.07
    ìĭľëĬĶ
    -0.07
    WRAPPER
    -0.06
    elan
    -0.06
     sticks
    -0.06
    मर
    -0.06
    avel
    -0.06
     mote
    -0.06
    Ø·ÙĨ
    -0.06
    POSITIVE LOGITS
     when
    0.08
     When
    0.07
     när
    0.07
    andas
    0.07
    unused
    0.06
     therefore
    0.06
     humans
    0.06
    ãĥķãĥĪ
    0.06
     these
    0.06
    .wp
    0.06
    Activations Density 0.040%

    No Known Activations