© 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. 108736
    Prev
    Next
    INDEX
    Explanations

    computer-generated text

    np_max-act · gemini-2.0-flash
    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
    dr
    -0.08
     forb
    -0.07
    된다
    -0.07
     Carl
    -0.07
     candid
    -0.07
    	template
    -0.07
    and
    -0.07
     politely
    -0.07
    br
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    X
    0.22
    x
    0.20
     X
    0.17
     x
    0.16
    ix
    0.15
    ax
    0.14
    ox
    0.14
    -X
    0.13
    ex
    0.13
    (X
    0.13
    Activations Density 0.239%

    No Known Activations