© 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. 14932
    Prev
    Next
    INDEX
    Explanations

    graphical notations and commands used in programming or technical documentation

    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
    ariant
    -0.07
     fas
    -0.07
    orraine
    -0.06
    oe
    -0.06
    alse
    -0.06
    pj
    -0.06
     fin
    -0.05
    ala
    -0.05
    orian
    -0.05
     æ¹
    -0.05
    POSITIVE LOGITS
    ẽ
    0.08
    .metamodel
    0.07
     GOODMAN
    0.07
    .scalablytyped
    0.07
    llib
    0.07
    rece
    0.07
    Ìģc
    0.07
    uitka
    0.07
    .hxx
    0.07
    _defs
    0.07
    Activations Density 0.016%

    No Known Activations