© 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. 87437
    Prev
    Next
    INDEX
    Explanations

    references to ceilings in various contexts

    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
    OrCreate
    -0.09
    zing
    -0.07
    vide
    -0.07
    caster
    -0.07
    rien
    -0.07
    dish
    -0.07
    eting
    -0.06
    .mixin
    -0.06
    ứng
    -0.06
    yyy
    -0.06
    POSITIVE LOGITS
    -mounted
    0.10
    egal
    0.08
    -ce
    0.08
    idla
    0.07
    /window
    0.07
    éĻħ
    0.07
    ecimal
    0.07
    /cloud
    0.07
    ights
    0.07
     raft
    0.07
    Activations Density 0.002%

    No Known Activations