© 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. 85775
    Prev
    Next
    INDEX
    Explanations

    connections between ideas and concepts in a narrative context

    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
    169
    -0.07
    abbo
    -0.07
    etroit
    -0.07
    arov
    -0.07
    atsby
    -0.07
    tok
    -0.07
    ặn
    -0.06
    abis
    -0.06
    Ãłng
    -0.06
    راÙĤ
    -0.06
    POSITIVE LOGITS
    throw
    0.07
    âm
    0.06
     magnet
    0.06
     cl
    0.06
    chant
    0.06
     designate
    0.06
    XD
    0.06
     desert
    0.06
    acos
    0.06
    ī
    0.06
    Activations Density 0.036%

    No Known Activations