© 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. 119060
    Prev
    Next
    INDEX
    Explanations

    your

    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
    áze
    -0.07
    brates
    -0.07
     emit
    -0.06
     device
    -0.06
    LoadIdentity
    -0.06
    AGEMENT
    -0.06
     generalize
    -0.06
     Monte
    -0.06
    ODEV
    -0.06
     Ebony
    -0.05
    POSITIVE LOGITS
    &#
    0.08
     drought
    0.07
     Ips
    0.07
    	cout
    0.07
    .ToDouble
    0.07
    -secondary
    0.06
     bourbon
    0.06
     شرایط
    0.06
    [:,
    0.06
    _specific
    0.06
    Activations Density 0.018%

    No Known Activations