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

    Neuronpedia

    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. 29855
    Prev
    Next
    INDEX
    Explanations

    expressions related to responsibility and consequences

    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
    iver
    -0.07
     Prem
    -0.07
    باÙĨ
    -0.07
    Prem
    -0.07
    (dead
    -0.06
     Rac
    -0.06
    oproject
    -0.06
    ?}",
    -0.06
    roof
    -0.06
    udit
    -0.06
    POSITIVE LOGITS
    opia
    0.06
    illo
    0.06
     retro
    0.06
     overseas
    0.06
     Ab
    0.06
     Country
    0.06
    uru
    0.06
    IfNeeded
    0.06
     foreign
    0.06
    611
    0.06
    Activations Density 0.008%

    No Known Activations