© 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. 22-LLAMASCOPE-RES-131K
    11. 4248
    Prev
    Next
    INDEX
    Explanations

    phrases related to immigration and travel regulations

    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
    aln
    -0.07
    enes
    -0.07
    anton
    -0.07
    év
    -0.07
    rons
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
     hoa
    -0.07
    amu
    -0.07
    áme
    -0.07
    inton
    -0.07
    POSITIVE LOGITS
     study
    0.16
     Study
    0.14
     studying
    0.14
    study
    0.14
    Study
    0.13
     Stud
    0.12
     studies
    0.12
     studied
    0.11
     visit
    0.11
     STUD
    0.11
    Activations Density 0.059%

    No Known Activations