© 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. 13466
    Prev
    Next
    INDEX
    Explanations

    Equity

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of the financial metric “Return on Assets (ROA),” including its constituent tokens like “Return,” “on,” “Assets,” “RO,” and “A.”

    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
     Skin
    -0.07
    	score
    -0.07
    ]));↵↵
    -0.06
    .LayoutStyle
    -0.06
     oversee
    -0.06
    >Welcome
    -0.06
     embassy
    -0.06
     frustrations
    -0.06
    .btnDelete
    -0.06
    cü
    -0.06
    POSITIVE LOGITS
    jít
    0.08
     قتل
    0.08
    /pdf
    0.07
     konci
    0.07
     careless
    0.07
     character
    0.06
     Patients
    0.06
     occult
    0.06
     PROVID
    0.06
     NFS
    0.06
    Activations Density 0.006%

    No Known Activations