© 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. 75573
    Prev
    Next
    INDEX
    Explanations

    actions related to searching or finding objects

    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
    bett
    -0.08
     said
    -0.07
    cx
    -0.06
     myster
    -0.06
     saying
    -0.06
     themselves
    -0.06
    raki
    -0.06
    wand
    -0.06
     and
    -0.05
     together
    -0.05
    POSITIVE LOGITS
     глÑĥ
    0.08
    -LAST
    0.08
     cazzo
    0.07
    ÑĢÑĮ
    0.07
    iya
    0.07
    ruz
    0.07
    :selected
    0.07
    ãĤįãģĨ
    0.07
    ëĿ¼ëıĦ
    0.07
    afort
    0.07
    Activations Density 0.016%

    No Known Activations