© 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. 106453
    Prev
    Next
    INDEX
    Explanations

    references to recommending a home inspection service

    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
     Gund
    -0.07
     often
    -0.06
    urn
    -0.06
    undry
    -0.06
     Lever
    -0.06
     imper
    -0.06
    irit
    -0.06
    wei
    -0.06
     grate
    -0.06
     usually
    -0.05
    POSITIVE LOGITS
     anyone
    0.08
    amerate
    0.08
     yourselves
    0.07
    gnore
    0.07
     ANY
    0.07
    Anyone
    0.07
    .weixin
    0.07
     any
    0.07
     anybody
    0.07
    رÙĥ
    0.06
    Activations Density 0.028%

    No Known Activations