© 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. 118955
    Prev
    Next
    INDEX
    Explanations

    interactions and responses from readers or users

    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
    996
    -0.07
    unas
    -0.06
    ul
    -0.06
    ut
    -0.06
    cri
    -0.06
    aoke
    -0.05
    ask
    -0.05
    utex
    -0.05
    agan
    -0.05
    ential
    -0.05
    POSITIVE LOGITS
    naments
    0.08
     jos
    0.07
    iglia
    0.07
    viso
    0.07
    ighth
    0.07
    ãĤ¤ãĥ¤
    0.07
    ucer
    0.07
    alu
    0.07
     célib
    0.06
    fer
    0.06
    Activations Density 0.001%

    No Known Activations