© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54081
    Prev
    Next
    INDEX
    Explanations

    Scientific/Technical texts

    np_max-act · gemini-2.0-flash

    The neuron fires on long, specialized chemical compound names (e.g. IUPAC‐style drug or molecule names).

    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
    CNN
    -0.06
    ieu
    -0.06
     이상
    -0.06
    Js
    -0.06
    urons
    -0.06
     nesting
    -0.06
     LZ
    -0.06
    _dropout
    -0.06
     curiosity
    -0.06
    э
    -0.06
    POSITIVE LOGITS
     tableLayoutPanel
    0.07
    }}>↵
    0.07
     �
    0.07
     rencont
    0.07
     edil
    0.07
     jobject
    0.07
    (rows
    0.07
                                    
    0.07
     즐
    0.06
     follando
    0.06
    Activations Density 0.076%

    No Known Activations