© 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. 62178
    Prev
    Next
    INDEX
    Explanations

    expressions of personal pronouns indicating the speaker's engagement and experiences

    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
    ãĥķãĤ
    -0.08
    út
    -0.08
    chts
    -0.07
    kos
    -0.07
    udit
    -0.07
    ABCDEFGHIJKLMNOP
    -0.06
    $MESS
    -0.06
    obili
    -0.06
    okies
    -0.06
    tres
    -0.06
    POSITIVE LOGITS
     shouldn
    0.06
     should
    0.06
     ought
    0.06
    è¦ģ
    0.06
     hãy
    0.06
    ï¼Įè¦ģ
    0.06
    483
    0.06
     could
    0.06
    é«
    0.06
    659
    0.06
    Activations Density 0.014%

    No Known Activations