© 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. 17-LLAMASCOPE-RES-131K
    11. 57799
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe unusual or unusual experiences

    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
    orges
    -0.07
    manship
    -0.06
    iesz
    -0.06
    antz
    -0.06
    illa
    -0.06
    isd
    -0.06
    andas
    -0.05
    elijke
    -0.05
    iese
    -0.05
    æĸ¹æ¡Ī
    -0.05
    POSITIVE LOGITS
    -shaped
    0.10
    ingly
    0.09
    weise
    0.08
    문
    0.08
     lạ
    0.08
     shaped
    0.07
    ily
    0.07
     peculiar
    0.07
    tc
    0.07
    /we
    0.07
    Activations Density 0.032%

    No Known Activations