© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 89823
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences related to struggles or confrontations with opposition

    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
    Tp
    -0.08
    unn
    -0.07
    jedn
    -0.07
     |[
    -0.07
    UEL
    -0.06
     insp
    -0.06
     NEGLIGENCE
    -0.06
    ľ
    -0.06
    piration
    -0.06
     вп
    -0.06
    POSITIVE LOGITS
     my
    0.06
    RuleContext
    0.06
     instead
    0.06
    ÃŁen
    0.05
    anton
    0.05
    midi
    0.05
    instead
    0.05
    dde
    0.05
    ervers
    0.05
    achen
    0.05
    Activations Density 0.003%

    No Known Activations