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. 84928
    Prev
    Next
    INDEX
    Explanations

    company acquisitions

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of entity ownership or corporate transactions (e.g. “owned by,” acquisitions, licensee changes).

    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
    /book
    -0.07
     mg
    -0.06
    	Document
    -0.06
     Saudis
    -0.06
    earth
    -0.06
     presets
    -0.06
    they
    -0.06
     contradiction
    -0.06
     dvěma
    -0.06
    .animate
    -0.06
    POSITIVE LOGITS
     interested
    0.07
    řil
    0.07
    	extern
    0.07
     accessible
    0.06
     hobby
    0.06
     غذ
    0.06
     boa
    0.06
     особенно
    0.06
     Zo
    0.06
    ━
    0.06
    Activations Density 0.023%

    No Known Activations