© 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. 129696
    Prev
    Next
    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash

    code snippets related to creating and manipulating forms in web development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on HTML tag attributes and their values (e.g. class=…, style=…, id=…, etc.), i.e. it detects attribute-assignment contexts in markup.

    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
    赫
    -0.06
     πό
    -0.06
    Ep
    -0.06
    _PI
    -0.06
     اون
    -0.06
    ثمان
    -0.06
     Lost
    -0.06
    France
    -0.06
    �
    -0.06
    ldr
    -0.06
    POSITIVE LOGITS
     Seite
    0.07
    ]}↵
    0.07
    "]))
    0.07
     humid
    0.07
    ']?></
    0.07
    кість
    0.06
    _DEPEND
    0.06
    //}}
    0.06
     приводит
    0.06
     listens
    0.06
    Activations Density 0.004%

    No Known Activations