© 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. 105173
    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
    chio
    -0.07
    ansi
    -0.07
    zac
    -0.06
    vet
    -0.06
    lemn
    -0.06
     poil
    -0.06
    jam
    -0.06
    tres
    -0.06
    ubi
    -0.06
    elu
    -0.06
    POSITIVE LOGITS
    orsch
    0.07
    )((((
    0.06
     nominate
    0.06
    Ñıк
    0.06
    .cli
    0.06
    254
    0.06
    .aspx
    0.06
    caption
    0.06
     NGX
    0.06
     pushViewController
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.