© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 9569
    Prev
    Next
    INDEX
    Explanations

    Cef- antibiotics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دارم
    -0.07
    	html
    -0.07
     "{{
    -0.06
    	set
    -0.06
    	CHECK
    -0.06
    bsub
    -0.06
    /.↵
    -0.06
    ){↵↵
    -0.06
     LaTeX
    -0.06
    ="%
    -0.06
    POSITIVE LOGITS
    _subject
    0.07
     eyed
    0.06
    /find
    0.06
    locate
    0.06
    thed
    0.06
     석
    0.06
    tbody
    0.06
     ;-
    0.06
     cooled
    0.06
     besonders
    0.06
    Activations Density 0.005%

    No Known Activations