© 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. 17-LLAMASCOPE-RES-131K
    11. 60092
    Prev
    Next
    INDEX
    Explanations

    quotes and dialogue within 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
    oho
    -0.08
    اذ
    -0.07
    gst
    -0.07
    adelphia
    -0.07
    utt
    -0.07
    Å¡t
    -0.06
    ahoo
    -0.06
    icast
    -0.06
    .cz
    -0.06
    Smarty
    -0.06
    POSITIVE LOGITS
     же
    0.07
     ведÑĮ
    0.07
    avin
    0.06
    linger
    0.06
    aley
    0.06
    /Object
    0.06
    isel
    0.06
    assis
    0.06
    PILE
    0.06
    adil
    0.06
    Activations Density 0.022%

    No Known Activations