© 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. 15-LLAMASCOPE-RES-131K
    11. 88029
    Prev
    Next
    INDEX
    Explanations

    terms related to confinement or containment

    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
    ging
    -0.07
    ãĥĨãĥ«
    -0.06
    fea
    -0.06
     Millenn
    -0.06
    noop
    -0.06
    foundland
    -0.06
    vak
    -0.06
    anova
    -0.06
    VEN
    -0.06
    kl
    -0.06
    POSITIVE LOGITS
    ément
    0.08
    inator
    0.07
    restricted
    0.07
    ä½ı
    0.07
    PCI
    0.07
    bles
    0.07
    alive
    0.07
    ayet
    0.07
    -contained
    0.07
    _restrict
    0.07
    Activations Density 0.012%

    No Known Activations