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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 84531
    Prev
    Next
    INDEX
    Explanations

    msg

    np_max-act · gemini-2.0-flash

    The neuron fires on gettext/PO file keywords (e.g. “msgid”, “msgstr”, “msg”, “str”) and thus detects translation‐file metadata markers.

    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
     decades
    -0.06
     Luz
    -0.06
    nes
    -0.06
    cir
    -0.06
     SEM
    -0.06
    oder
    -0.06
     decade
    -0.06
    �
    -0.06
    ιστή
    -0.06
     edu
    -0.06
    POSITIVE LOGITS
    langs
    0.07
    createView
    0.07
     +#+#+#+#+#+
    0.07
    			               
    0.06
    (ValueError
    0.06
    (KeyCode
    0.06
     '{}'
    0.06
     disillusion
    0.06
    -----------*/↵
    0.06
     commented
    0.06
    Activations Density 0.000%

    No Known Activations