© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8816
    Prev
    Next
    INDEX
    Explanations

    good

    np_max-act · gemini-2.0-flash

    expressions of respectful communication and support in relationships.

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

    The neuron is detecting tokens that occur toward the end of the assistant’s responses (i.e. later positions in the output sequence).

    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
    ##_
    -0.06
     combin
    -0.06
    ُم
    -0.06
    Hom
    -0.06
    Objects
    -0.06
     supra
    -0.06
    .sound
    -0.06
    =*/
    -0.06
    _alloc
    -0.06
     suspected
    -0.06
    POSITIVE LOGITS
     interception
    0.07
     quân
    0.07
    terrorism
    0.07
     sigue
    0.06
     noir
    0.06
     besonders
    0.06
    job
    0.06
    getRepository
    0.06
     Unique
    0.06
    .hamcrest
    0.06
    Activations Density 0.064%

    No Known Activations