© 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. 41027
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direction, progression, or development

    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
    orthy
    -0.07
    sonian
    -0.07
    ASF
    -0.06
    652
    -0.06
    á»ij
    -0.06
     stran
    -0.06
    ÌĨ
    -0.06
    ãĥªãĥ¼ãĤº
    -0.06
     Τε
    -0.06
    _FOREACH
    -0.06
    POSITIVE LOGITS
     thereafter
    0.13
     then
    0.11
    ãģĿãģĵ
    0.09
     THEN
    0.09
     Then
    0.09
     subsequently
    0.08
    çĦ¶åIJİ
    0.08
     заÑĤем
    0.08
    _then
    0.08
    then
    0.08
    Activations Density 0.081%

    No Known Activations