© 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. 73662
    Prev
    Next
    INDEX
    Explanations

    public places

    np_max-act · gemini-2.0-flash

    The neuron detects named entities denoting institutions or formal organizations (e.g. schools, banks, cemeteries).

    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
     أج
    -0.07
    .Slice
    -0.06
     URLRequest
    -0.06
    อำนวย
    -0.06
    KeyValuePair
    -0.06
    =E
    -0.06
    subtract
    -0.06
     <?=$
    -0.06
    こそ
    -0.06
     Winn
    -0.06
    POSITIVE LOGITS
     monetary
    0.08
     viewpoint
    0.08
    radi
    0.07
    **
    0.07
     filtered
    0.07
     photographer
    0.07
     Countries
    0.07
    )
    0.07
    [
    0.07
     Student
    0.06
    Activations Density 0.047%

    No Known Activations