© 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. 91616
    Prev
    Next
    INDEX
    Explanations

    bp fragment

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of PCR‐based fragment length polymorphism assays—especially the terms “fragment,” “length,” “polymorphism,” and the associated base‐pair (bp) fragment sizes.

    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
     starring
    -0.06
    és
    -0.06
    JS
    -0.06
     kosten
    -0.06
    Coding
    -0.06
     aalborg
    -0.06
    é
    -0.06
    سين
    -0.06
    in
    -0.06
     Burlington
    -0.06
    POSITIVE LOGITS
    ับท
    0.07
     nelze
    0.07
     valeur
    0.07
    iky
    0.07
    potential
    0.07
     converts
    0.07
    hosts
    0.07
     conspiracy
    0.07
     Copyright
    0.06
    -runner
    0.06
    Activations Density 0.005%

    No Known Activations