© 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. 22-LLAMASCOPE-RES-131K
    11. 4239
    Prev
    Next
    INDEX
    Explanations

    physical actions involving interactions with objects or people

    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
    pdf
    -0.06
     bedrooms
    -0.06
    ìļ´ëį°
    -0.06
    nock
    -0.06
    andom
    -0.06
    å¾Ħ
    -0.06
     skies
    -0.06
     Mods
    -0.06
    PDF
    -0.06
     tunnels
    -0.06
    POSITIVE LOGITS
     railing
    0.11
     rail
    0.10
     wall
    0.10
    wall
    0.09
    rail
    0.09
     posts
    0.08
    æŁ±
    0.08
     edge
    0.08
    .wall
    0.08
    æī¶
    0.08
    Activations Density 0.038%

    No Known Activations