Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 50984
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron detects recommendation or suggestion phrases guiding the user to choose the best option.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code snippets that demonstrate the implementation of specific programming tasks or functionalities.

    oai_token-act-pair · gpt-4o-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
    Dictionary
    -0.07
    -negative
    -0.06
    Alg
    -0.06
    _eff
    -0.06
     झ
    -0.06
     tuple
    -0.06
     بند
    -0.06
     aspiration
    -0.06
    zv
    -0.06
     arrangement
    -0.06
    POSITIVE LOGITS
     bustling
    0.07
    bugs
    0.07
    vyšší
    0.07
     misled
    0.07
    ↵↵
    0.06
    んで
    0.06
    instanc
    0.06
    ी।
    0.06
     🙂↵↵
    0.06
     gi�
    0.06
    Activations Density 0.040%

    No Known Activations