© 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. 55412
    Prev
    Next
    INDEX
    Explanations

    that this

    np_max-act · gemini-2.0-flash

    The neuron activates on transitional/discourse cues—especially the phrase “with that” (as in “With that in mind” or “With that said”).

    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
    intersect
    -0.06
     affecting
    -0.06
    -times
    -0.06
     places
    -0.06
     Mostly
    -0.06
     contributed
    -0.06
     NONINFRINGEMENT
    -0.06
     Golf
    -0.06
     children
    -0.06
    _De
    -0.05
    POSITIVE LOGITS
     contentType
    0.07
    /msg
    0.07
    独
    0.06
     μον
    0.06
    ig
    0.06
     جد
    0.06
     چین
    0.06
    門
    0.06
    matic
    0.06
    Frameworks
    0.06
    Activations Density 0.009%

    No Known Activations