© 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. 126447
    Prev
    Next
    INDEX
    Explanations

    terms related to government and legal administration

    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
    .functional
    -0.07
    ninger
    -0.07
    ãĥĥãĤ¯ãĤ¹
    -0.06
    _Version
    -0.06
    izzo
    -0.06
    ãn
    -0.06
    ĥ
    -0.06
     же
    -0.06
    odu
    -0.06
    (strtolower
    -0.06
    POSITIVE LOGITS
    -aos
    0.06
    WC
    0.06
    nal
    0.06
    ledik
    0.06
    ört
    0.06
    uluk
    0.06
     terr
    0.06
    .qq
    0.06
     reputable
    0.06
    LT
    0.06
    Activations Density 0.001%

    No Known Activations