© 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. 128749
    Prev
    Next
    INDEX
    Explanations

    references to database operations and structures

    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
    ency
    -0.06
    vr
    -0.06
     edit
    -0.06
    è¾
    -0.06
    glas
    -0.06
    .readLine
    -0.06
    Ĺ
    -0.06
     subtree
    -0.06
    lass
    -0.06
    .ToShort
    -0.06
    POSITIVE LOGITS
    \Migration
    0.11
     Migration
    0.10
     migrations
    0.10
     migration
    0.09
     schema
    0.09
    /schema
    0.09
    Migration
    0.09
    ddl
    0.08
    igrations
    0.08
    phinx
    0.08
    Activations Density 0.039%

    No Known Activations