© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7014
    Prev
    Next
    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash

    technical terms and mathematical terminology related to advanced concepts in computational theories.

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

    The neuron detects the vertical bar character “|” used as the delimiter immediately following the “abstract:” label in scholarly papers.

    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
    [].
    -0.07
     insertion
    -0.06
     TMZ
    -0.06
     frantic
    -0.06
    {}.
    -0.06
    prev
    -0.06
    ementia
    -0.06
     řed
    -0.06
     Obst
    -0.06
    POSITIVE LOGITS
     concept
    0.06
    /Game
    0.06
    ви
    0.06
    #ab
    0.06
    URIComponent
    0.06
    -states
    0.06
    uzzer
    0.06
     extension
    0.06
    	script
    0.06
    іка
    0.06
    Activations Density 0.001%

    No Known Activations