© 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. 105327
    Prev
    Next
    INDEX
    Explanations

    references to accessibility and services available to the public

    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
    ezi
    -0.07
     McCorm
    -0.06
    isle
    -0.06
    567
    -0.06
     analog
    -0.06
     analogue
    -0.06
    ouz
    -0.06
    egie
    -0.05
    iddi
    -0.05
     Heights
    -0.05
    POSITIVE LOGITS
     public
    0.16
     PUBLIC
    0.14
    .public
    0.13
    public
    0.13
     Public
    0.13
    åħ¬
    0.13
     veÅĻej
    0.13
     pública
    0.12
    -public
    0.12
     pubb
    0.12
    Activations Density 0.033%

    No Known Activations