© 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. 118853
    Prev
    Next
    INDEX
    Explanations

    legislative terms and references to governmental facilities

    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
    flen
    -0.07
    orb
    -0.07
    811
    -0.06
    ÏĦα
    -0.06
    ixin
    -0.06
    AGER
    -0.06
    alen
    -0.06
    annel
    -0.06
     Interr
    -0.06
    αÏĢÏĮ
    -0.06
    POSITIVE LOGITS
    .cgi
    0.07
    ildo
    0.07
    è¦ļ
    0.06
    .Unity
    0.06
     Bord
    0.06
     facility
    0.06
    chn
    0.05
    ìļ°ìĬ¤
    0.05
    agram
    0.05
    atoon
    0.05
    Activations Density 0.015%

    No Known Activations