© 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. 87912
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a direct or honest manner of expression

    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
    mits
    -0.08
    sein
    -0.08
    mun
    -0.08
    Ìĥ
    -0.07
    ildo
    -0.07
    ocities
    -0.07
    munition
    -0.07
    avier
    -0.06
    hum
    -0.06
    _Init
    -0.06
    POSITIVE LOGITS
     straight
    0.08
    ened
    0.08
    er
    0.08
    Straight
    0.07
     Straight
    0.07
    缴
    0.07
    straight
    0.07
    aus
    0.07
    ening
    0.07
    ness
    0.07
    Activations Density 0.018%

    No Known Activations