© 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. 71429
    Prev
    Next
    INDEX
    Explanations

    information about insurance savings and discounts

    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
    çĽĺ
    -0.08
    lei
    -0.07
    ibri
    -0.07
    lou
    -0.07
    ÅĽmy
    -0.07
    .Contract
    -0.07
    ίνα
    -0.07
    ãĥ³ãĥĸ
    -0.07
     æ´
    -0.07
    ogan
    -0.07
    POSITIVE LOGITS
    cool
    0.06
    CO
    0.06
     demonstrations
    0.06
    orus
    0.06
     lump
    0.06
    letcher
    0.05
    aight
    0.05
     demonstration
    0.05
     steering
    0.05
     Organization
    0.05
    Activations Density 0.007%

    No Known Activations