© 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. 124434
    Prev
    Next
    INDEX
    Explanations

    pronouns related to personal identity and reference

    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
    коз
    -0.07
    _READONLY
    -0.07
    çĦ¦
    -0.07
    $MESS
    -0.07
    azer
    -0.07
    artz
    -0.07
    loo
    -0.07
    ãĥ³ãĤ¬
    -0.07
    chied
    -0.06
    ÑĤож
    -0.06
    POSITIVE LOGITS
     or
    0.13
    /her
    0.09
    /she
    0.09
    æĪĸ
    0.08
     oder
    0.07
    ãģ¾ãģŁãģ¯
    0.07
    /
    0.07
     atau
    0.06
     или
    0.06
     nebo
    0.06
    Activations Density 0.036%

    No Known Activations