© 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. 126245
    Prev
    Next
    INDEX
    Explanations

    vector

    np_max-act · gemini-2.0-flash

    technical terms and concepts related to vector mathematics and machine learning.

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

    This neuron fires whenever the word “vector” appears.

    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
     haline
    -0.07
    ��
    -0.07
    arta
    -0.07
    _TypeInfo
    -0.07
    NO
    -0.07
     finished
    -0.07
    ayne
    -0.07
     nen
    -0.06
    ne
    -0.06
    รม
    -0.06
    POSITIVE LOGITS
     Vector
    0.13
    vector
    0.12
     vector
    0.11
    Vector
    0.10
    vec
    0.10
    _vector
    0.10
    	Vector
    0.10
    .Vector
    0.10
     vectors
    0.10
     QVector
    0.09
    Activations Density 0.014%

    No Known Activations