© 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. 39798
    Prev
    Next
    INDEX
    Explanations

    construct

    np_max-act · gemini-2.0-flash

    mentions of construct validity or discussions about psychometric validity in research 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
     Mary
    -0.07
    _tcp
    -0.07
     manganese
    -0.06
     sampled
    -0.06
     trajectory
    -0.06
     ledna
    -0.06
     Temperature
    -0.06
     magnetic
    -0.06
    negative
    -0.06
    Mary
    -0.06
    POSITIVE LOGITS
     건
    0.09
     constructs
    0.09
     Construct
    0.08
     использ
    0.08
    Construct
    0.07
     construct
    0.07
    925
    0.07
     �
    0.07
    건
    0.07
     Rece
    0.07
    Activations Density 0.004%

    No Known Activations