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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77003
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or position

    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
    ç«
    -0.08
    otch
    -0.08
    coon
    -0.07
    inke
    -0.07
    ÙĪÙħاÙĨ
    -0.07
    ÑĢÑĸÑĩ
    -0.07
    bao
    -0.07
    osate
    -0.07
    enga
    -0.07
    atif
    -0.07
    POSITIVE LOGITS
     Som
    0.07
     the
    0.06
     premises
    0.06
    mas
    0.06
     frequ
    0.06
     Urs
    0.06
    nie
    0.06
    (Response
    0.06
     Uph
    0.05
     Sn
    0.05
    Activations Density 0.035%

    No Known Activations