© 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 EvalsExportsinterp-engineNEWAPI 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. 14716
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "my" and related possessive pronouns

    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
    пон
    -0.08
    .ov
    -0.07
     ãĢij
    -0.07
    orce
    -0.07
    ppo
    -0.07
    ovice
    -0.06
    ovation
    -0.06
    ipt
    -0.06
    顾
    -0.06
    رÙĤ
    -0.06
    POSITIVE LOGITS
     aim
    0.10
     goal
    0.09
    oret
    0.08
    缮
    0.08
    rna
    0.07
     only
    0.07
     hope
    0.07
    agine
    0.07
     term
    0.07
    goal
    0.07
    Activations Density 0.029%

    No Known Activations