© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 126610
    Prev
    Next
    INDEX
    Explanations

    names of states along with associated statistics or data

    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
    fcn
    -0.07
    oulouse
    -0.07
     nz
    -0.07
    noise
    -0.07
    nze
    -0.07
    amina
    -0.07
     Johannesburg
    -0.06
    .nz
    -0.06
    éo
    -0.06
     downtown
    -0.06
    POSITIVE LOGITS
     states
    0.09
    states
    0.07
     Washing
    0.07
     STATES
    0.06
    uguay
    0.06
     Tester
    0.06
     estados
    0.06
     ÑĪÑĤ
    0.06
    Ill
    0.06
    States
    0.06
    Activations Density 0.012%

    No Known Activations