© 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. 118401
    Prev
    Next
    INDEX
    Explanations

    terms related to aerosols and their interactions in environmental and nuclear contexts

    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
    ãģĬ
    -0.06
    ew
    -0.06
    :UIAlert
    -0.06
    isen
    -0.05
     Hick
    -0.05
    æ¢
    -0.05
     tack
    -0.05
     endian
    -0.05
    criptor
    -0.05
     Bend
    -0.05
    POSITIVE LOGITS
    olland
    0.08
    imei
    0.08
    entai
    0.08
    earer
    0.07
    .rpm
    0.07
    earing
    0.07
     population
    0.07
    ProgressHUD
    0.07
    械
    0.07
    éĺħ读次æķ°
    0.07
    Activations Density 0.063%

    No Known Activations