© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44182
    Prev
    Next
    INDEX
    Explanations

    business restructuring and turnaround

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect terms and phrases related to organizational change and restructuring (e.g. transformation, reorganization, reboot, modernize).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jsonData
    -0.07
     CallingConvention
    -0.06
     Stmt
    -0.06
     "));↵
    -0.06
    _version
    -0.06
    .pa
    -0.06
     такими
    -0.06
    Ctrls
    -0.06
     requirement
    -0.06
    	Command
    -0.06
    POSITIVE LOGITS
     плит
    0.07
    .Linq
    0.07
     Grat
    0.06
    _basis
    0.06
    _Re
    0.06
    ीव
    0.06
     Aberdeen
    0.06
     هل
    0.06
    річ
    0.06
     dönüş
    0.06
    Activations Density 0.065%

    No Known Activations