© 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. 8906
    Prev
    Next
    INDEX
    Explanations

    reference standards

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on phrasing that designates a reference (“gold standard”) method—e.g. “CT as a gold standard” or “X-ray angiography as the reference standard.”

    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
    atorium
    -0.06
    ontology
    -0.06
     deployment
    -0.06
     randomness
    -0.06
     تشکیل
    -0.06
     authorization
    -0.06
    _distribution
    -0.05
     montage
    -0.05
    	index
    -0.05
    Administrator
    -0.05
    POSITIVE LOGITS
    анія
    0.07
    AsyncResult
    0.07
    Mich
    0.07
    SED
    0.06
     itr
    0.06
    utschen
    0.06
    CPU
    0.06
    icago
    0.06
    řet
    0.06
    OVÁ
    0.06
    Activations Density 0.027%

    No Known Activations