© 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. 15-LLAMASCOPE-RES-131K
    6. 88971
    Prev
    Next
    INDEX
    Explanations

    terms related to communication technologies and processes

    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
    usher
    -0.07
    odash
    -0.07
    álo
    -0.07
    rame
    -0.06
    nan
    -0.06
    adt
    -0.06
    eature
    -0.06
    nop
    -0.06
    ingham
    -0.06
    ALLED
    -0.06
    POSITIVE LOGITS
    ữa
    0.07
    gable
    0.07
    ê¶Į
    0.06
    å³
    0.06
     WCHAR
    0.06
    имо
    0.06
    ovan
    0.06
    MMdd
    0.06
    dera
    0.06
     íĽĦë³´
    0.06
    Activations Density 0.020%

    No Known Activations