© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4279
    Prev
    Next
    INDEX
    Explanations

    references to notable deaths

    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
    vÄĽt
    -0.07
     blinds
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
     smrt
    -0.06
    ä»®
    -0.06
     DEAD
    -0.06
     Král
    -0.06
     carry
    -0.06
    iverz
    -0.06
    ãĤ¹ãĥ¬
    -0.06
    POSITIVE LOGITS
     persons
    0.08
    ÑĢик
    0.07
    人çī©
    0.07
    estination
    0.07
     Person
    0.06
     person
    0.06
     during
    0.06
    portun
    0.06
     Persons
    0.06
    .operations
    0.06
    Activations Density 0.001%

    No Known Activations