© 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. 9-LLAMASCOPE-RES-131K
    6. 95865
    Prev
    Next
    INDEX
    Explanations

    specifications and parameters related to image processing

    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
    ber
    -0.06
    Ìĥ
    -0.06
    abor
    -0.06
    illon
    -0.06
    ander
    -0.06
    aser
    -0.06
    der
    -0.06
    nder
    -0.06
     ihr
    -0.06
    heit
    -0.05
    POSITIVE LOGITS
    éĭ
    0.08
    Ïĩή
    0.07
     rencont
    0.07
    Äįan
    0.07
    گاÙĨ
    0.07
    ãĥ¼ãĥį
    0.07
    apel
    0.07
    _pdata
    0.07
    enor
    0.07
    iners
    0.07
    Activations Density 0.007%

    No Known Activations