© 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. 15-LLAMASCOPE-RES-131K
    6. 26927
    Prev
    Next
    INDEX
    Explanations

    terms related to linguistic structure, particularly prefixes and suffixes

    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
    876
    -0.07
    uset
    -0.07
    erli
    -0.07
    RetVal
    -0.06
    hausen
    -0.06
    pla
    -0.06
    IFI
    -0.06
     comma
    -0.06
    xec
    -0.06
     NoSuch
    -0.06
    POSITIVE LOGITS
    _PUS
    0.07
    erner
    0.07
    ADDE
    0.06
    morph
    0.06
    ernes
    0.06
     Beverage
    0.06
    ëĬ¥
    0.06
     morph
    0.06
     æ°
    0.06
    _processes
    0.06
    Activations Density 0.005%

    No Known Activations