© 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. 108486
    Prev
    Next
    INDEX
    Explanations

    phrases related to the action of registering or enrolling for something

    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
    akis
    -0.07
    egr
    -0.07
    etta
    -0.06
    akt
    -0.06
    igits
    -0.06
    /from
    -0.06
    boa
    -0.06
    avern
    -0.06
    inic
    -0.06
    union
    -0.06
    POSITIVE LOGITS
     for
    0.08
    839
    0.07
    _globals
    0.07
    ivate
    0.07
    /***/
    0.07
    .easing
    0.07
    nage
    0.06
     forKey
    0.06
    dbus
    0.06
     EINA
    0.06
    Activations Density 0.008%

    No Known Activations