© 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. 93765
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to forgiveness

    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
     rang
    -0.07
    ially
    -0.07
    trim
    -0.07
    peg
    -0.07
    ucas
    -0.06
    alan
    -0.06
    ppers
    -0.06
    LT
    -0.06
    ropa
    -0.06
    ifax
    -0.06
    POSITIVE LOGITS
    otten
    0.08
    ays
    0.07
    isser
    0.07
    518
    0.07
    achine
    0.07
    ueil
    0.07
    ues
    0.07
    ough
    0.07
    warn
    0.06
    amina
    0.06
    Activations Density 0.005%

    No Known Activations