© 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. 129941
    Prev
    Next
    INDEX
    Explanations

    virtual

    np_max-act · gemini-2.0-flash

    mentions of virtual-reality/simulation technologies and their related haptic/teleoperation contexts.

    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
    まる
    -0.07
    licate
    -0.07
     murder
    -0.07
     WK
    -0.07
    -orders
    -0.07
     kills
    -0.06
    ete
    -0.06
    ller
    -0.06
    inae
    -0.06
    アー
    -0.06
    POSITIVE LOGITS
    umhur
    0.06
    BCM
    0.06
     SendMessage
    0.06
     Coalition
    0.06
     Italians
    0.06
    mesh
    0.06
    olet
    0.06
    iento
    0.06
     InvalidOperationException
    0.05
     Gim
    0.05
    Activations Density 0.011%

    No Known Activations