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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 84581
    Prev
    Next
    INDEX
    Explanations

    ld

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of software/daemon command names ending in “d” (e.g. mysqld, sshd, tcp_wrappers).

    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
    .loadtxt
    -0.06
     bananas
    -0.06
    ano
    -0.06
     layouts
    -0.06
     nan
    -0.06
    ,cljs
    -0.06
    .property
    -0.06
     stří
    -0.06
    _unc
    -0.06
    あの
    -0.06
    POSITIVE LOGITS
     writers
    0.06
     Wert
    0.06
     СРСР
    0.06
     <↵
    0.06
    큼
    0.06
     squads
    0.06
    working
    0.06
    ompiler
    0.06
    	assertNotNull
    0.06
     Said
    0.06
    Activations Density 0.008%

    No Known Activations