© 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. 128899
    Prev
    Next
    INDEX
    Explanations

    phrases indicating blame or accusation

    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
    LOCAL
    -0.07
    ANGES
    -0.06
    pellier
    -0.06
    ruk
    -0.06
     LOCAL
    -0.06
     лок
    -0.06
    hev
    -0.06
    roj
    -0.06
    DNA
    -0.06
     Local
    -0.06
    POSITIVE LOGITS
    ugins
    0.08
    ugin
    0.08
    ington
    0.07
    dfa
    0.07
    olini
    0.06
    metis
    0.06
     Revolutionary
    0.06
     verb
    0.06
    æ°
    0.06
     NEC
    0.06
    Activations Density 0.000%

    No Known Activations