© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 28117
    Prev
    Next
    INDEX
    Explanations

    HTML or XML attribute values

    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
    ignon
    -0.07
    igr
    -0.06
    207
    -0.06
    %f
    -0.06
    act
    -0.06
    oble
    -0.06
    éĹŃ
    -0.05
    554
    -0.05
     Hi
    -0.05
    cri
    -0.05
    POSITIVE LOGITS
    amaño
    0.07
     >",
    0.07
     ninh
    0.07
    cÃŃ
    0.07
    erno
    0.07
    uco
    0.07
    adol
    0.07
    rowable
    0.07
    enor
    0.06
    chema
    0.06
    Activations Density 0.001%

    No Known Activations