Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 84745
    Prev
    Next
    INDEX
    Explanations

    verte

    np_max-act · gemini-2.0-flash

    references to proteins and their functions related to cellular processes.

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

    The neuron detects mentions of vertebrate (especially mammalian) organisms.

    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
    Yeah
    -0.07
    ayo
    -0.06
     ederek
    -0.06
     Ih
    -0.06
     rapidly
    -0.06
    ullah
    -0.06
    apest
    -0.06
    ovými
    -0.06
    _fecha
    -0.06
     hallmark
    -0.06
    POSITIVE LOGITS
    _tele
    0.06
    als
    0.06
    ::↵↵
    0.06
    із
    0.06
    subtitle
    0.06
    'order
    0.06
    ्क
    0.06
    .bank
    0.06
     Taco
    0.06
    omentum
    0.06
    Activations Density 0.008%

    No Known Activations