© 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. 73734
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    technical references to coding and programming concepts.

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

    This neuron responds to floating-point or decimal-number tokens in the text.

    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
    —"
    -0.07
    :|
    -0.06
     perror
    -0.06
     příro
    -0.06
    Translate
    -0.06
     grape
    -0.06
     vandalism
    -0.06
    .Payload
    -0.06
     Philosophy
    -0.06
     offic
    -0.06
    POSITIVE LOGITS
    credentials
    0.07
    _Account
    0.06
    HasMaxLength
    0.06
    TestClass
    0.06
     lacking
    0.06
    zza
    0.06
    _horizontal
    0.06
    Dyn
    0.06
    .DriverManager
    0.06
    ンガ
    0.06
    Activations Density 0.160%

    No Known Activations