© 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. 93756
    Prev
    Next
    INDEX
    Explanations

    concepts related to employee relocation and market evaluation

    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
    tek
    -0.08
    onet
    -0.07
     everybody
    -0.07
    лÑĸв
    -0.07
     someone
    -0.06
     somebody
    -0.06
     mis
    -0.06
     your
    -0.06
    ’ll
    -0.06
    zn
    -0.06
    POSITIVE LOGITS
    оваÑĢ
    0.07
    訳
    0.07
    odore
    0.07
    ãģ»ãģĨ
    0.06
    èĥ½å¤Ł
    0.06
    hips
    0.06
     pomÄĽrnÄĽ
    0.06
    http
    0.06
     Äijá»ĵ
    0.06
    à¹ĩà¸Ķ
    0.06
    Activations Density 0.004%

    No Known Activations