© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27387
    Prev
    Next
    INDEX
    Explanations

    punctuations and sentence endings

    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
     CONSEQUENTIAL
    -0.06
    erging
    -0.06
     FileType
    -0.06
     RESERVED
    -0.06
    ious
    -0.06
    zin
    -0.06
    _Cmd
    -0.06
     Parliament
    -0.06
    haus
    -0.06
    arshal
    -0.06
    POSITIVE LOGITS
    ureau
    0.07
    (HWND
    0.06
    ocator
    0.06
    esel
    0.06
    aura
    0.06
    ottes
    0.06
    rypton
    0.06
    Ĥ¨
    0.06
    ä¸įäºĨ
    0.06
    деÑĤ
    0.06
    Activations Density 0.114%

    No Known Activations