© 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 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. 87383
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ге
    -0.07
    ÅĽÄĩ
    -0.07
    ãĥįãĥ«
    -0.07
    spb
    -0.07
    _UNDEFINED
    -0.07
    podob
    -0.07
     Franklin
    -0.07
    xec
    -0.07
    _firestore
    -0.07
     tolua
    -0.06
    POSITIVE LOGITS
    971
    0.06
    iami
    0.06
    lycer
    0.06
    mes
    0.06
    ars
    0.06
     Usage
    0.06
    jun
    0.05
     mes
    0.05
    obot
    0.05
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.