© 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. 89283
    Prev
    Next
    INDEX
    Explanations

    phrases related to candidate selection and job applications

    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
    sr
    -0.06
    baugh
    -0.06
    ogg
    -0.06
    stick
    -0.06
    สาร
    -0.06
    icip
    -0.06
    ZY
    -0.06
    .exchange
    -0.06
    poi
    -0.06
    çªģ
    -0.06
    POSITIVE LOGITS
     someone
    0.14
     whoever
    0.13
     Whoever
    0.13
     winner
    0.13
    someone
    0.13
     somebody
    0.12
     Someone
    0.12
    Someone
    0.11
    winner
    0.11
     Winner
    0.11
    Activations Density 0.045%

    No Known Activations