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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 126473
    Prev
    Next
    INDEX
    Explanations

    mortgages

    np_max-act · gemini-2.0-flash

    The neuron flags terms related to the subprime‐mortgage housing crisis (e.g., subprime, mortgages, foreclosures, housing).

    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
    atalog
    -0.07
    relationships
    -0.07
    enterprise
    -0.07
     coup
    -0.07
     Regel
    -0.07
    Mix
    -0.07
    cona
    -0.07
     Bağ
    -0.07
    cript
    -0.06
    媒
    -0.06
    POSITIVE LOGITS
    accessToken
    0.06
     Jian
    0.06
    ',...↵
    0.06
    .IsDBNull
    0.06
    -Identifier
    0.06
    繁
    0.06
    _tile
    0.06
     ><?
    0.06
     ghosts
    0.05
     screenWidth
    0.05
    Activations Density 0.013%

    No Known Activations