© 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. 17-LLAMASCOPE-RES-131K
    6. 78272
    Prev
    Next
    INDEX
    Explanations

    references to real estate and financial advising

    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
     Enrollment
    -0.07
     lamp
    -0.07
     Bracket
    -0.06
    icus
    -0.06
    lamp
    -0.06
    AGO
    -0.06
     "'"
    -0.06
     Bradford
    -0.06
     enrollment
    -0.06
    CHIP
    -0.06
    POSITIVE LOGITS
     regulator
    0.07
    .gf
    0.07
    Apis
    0.07
    Handled
    0.07
    .digest
    0.06
     Scheme
    0.06
    ularity
    0.06
     Cousins
    0.06
     Soph
    0.06
     Hutch
    0.06
    Activations Density 0.012%

    No Known Activations