© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41689
    Prev
    Next
    INDEX
    Explanations

    code and dataframes

    np_max-act · gemini-2.0-flash

    The neuron is detecting the presence of code snippets or code‐block markers (e.g. backticks, triple‐backticks, language annotations) in the text.

    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
     Stainless
    -0.07
     refusal
    -0.07
     dent
    -0.06
     Cors
    -0.06
    .Command
    -0.06
     Gemini
    -0.06
    Throw
    -0.06
    -property
    -0.06
    .userId
    -0.06
    Details
    -0.06
    POSITIVE LOGITS
     kita
    0.08
     kil
    0.07
    보다
    0.06
     iç
    0.06
    unct
    0.06
     Multi
    0.06
    CanBeConverted
    0.06
    		
    ↵
    ↵
    0.06
     ChatColor
    0.06
    žití
    0.06
    Activations Density 0.028%

    No Known Activations