© 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. 797
    Prev
    Next
    INDEX
    Explanations

    chemical synthesis

    np_max-act · gemini-2.0-flash

    chemical compounds and synthesis processes involved in the production of pharmaceuticals.

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

    This neuron activates on parts of systematic chemical compound names—especially multi-digit, hyphenated IUPAC 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
     που
    -0.07
    	return
    -0.07
    のだろう
    -0.06
    �
    -0.06
    พวก
    -0.06
    ایش
    -0.06
    علام
    -0.06
    igDecimal
    -0.06
    альна
    -0.06
    Filled
    -0.06
    POSITIVE LOGITS
     Sloven
    0.07
    .cc
    0.07
     จ
    0.07
     MainForm
    0.06
    (Display
    0.06
     Friedrich
    0.06
    .train
    0.06
    侍
    0.06
    .Result
    0.06
    crit
    0.06
    Activations Density 0.094%

    No Known Activations