© 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. 6536
    Prev
    Next
    INDEX
    Explanations

    Header

    np_max-act · gemini-2.0-flash

    The neuron activates on code identifiers for metadata or header fields—e.g. “Header,” “Hdr,” “Meta,” “ObjectMeta,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code snippets related to networking and data packaging.

    oai_token-act-pair · gpt-4o-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
     Payload
    -0.07
     mgr
    -0.06
     nightly
    -0.06
    axis
    -0.06
    Threads
    -0.06
    Anal
    -0.06
    Test
    -0.06
     أس
    -0.06
    arus
    -0.06
    alus
    -0.06
    POSITIVE LOGITS
     assertFalse
    0.07
    _PROF
    0.06
     radioButton
    0.06
    /module
    0.06
    battle
    0.06
     CNS
    0.06
    (((
    0.06
    POP
    0.06
    _include
    0.06
     appearances
    0.06
    Activations Density 0.017%

    No Known Activations