© 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. 7-RESID-POST-AA
    11. 86286
    Prev
    Next
    INDEX
    Explanations

    agent

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of "agent" (including its morphological and compound forms) in text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    425
    -0.08
     Romero
    -0.08
    itud
    -0.07
     лік
    -0.07
     II
    -0.07
    (city
    -0.07
    303
    -0.07
     hill
    -0.07
    idential
    -0.07
    575
    -0.07
    POSITIVE LOGITS
     agent
    0.19
     agents
    0.18
     Agent
    0.18
     Agents
    0.14
    Agent
    0.13
    -agent
    0.13
    agent
    0.12
    Agents
    0.10
    _agents
    0.09
    _agent
    0.09
    Activations Density 0.016%

    No Known Activations