© 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. 61442
    Prev
    Next
    INDEX
    Explanations

    specific postal or location information

    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
    ãĥ¬ãĥĥãĥĪ
    -0.09
    ettel
    -0.08
    ãĥ«ãĤ¯
    -0.08
    GuidId
    -0.07
    soles
    -0.07
    vrier
    -0.07
    znám
    -0.07
    altet
    -0.07
    unsch
    -0.07
    neau
    -0.07
    POSITIVE LOGITS
    -fw
    0.06
    isan
    0.06
     conf
    0.06
    μοÏĤ
    0.05
    ym
    0.05
    aku
    0.05
     vent
    0.05
     crafts
    0.05
    ABI
    0.05
    ÃŃna
    0.05
    Activations Density 0.000%

    No Known Activations