Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 106751
    Prev
    Next
    INDEX
    Explanations

    around

    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
    	Write
    -0.07
     बज
    -0.07
     되어
    -0.07
    .objects
    -0.06
    世界
    -0.06
    →→
    -0.06
    είτε
    -0.06
     Weiter
    -0.06
    ازل
    -0.06
    анию
    -0.06
    POSITIVE LOGITS
    Truth
    0.07
     justo
    0.06
    (prob
    0.06
     Mass
    0.06
    дром
    0.06
     implicitly
    0.06
     barber
    0.06
    unct
    0.06
     Ampl
    0.06
     Sex
    0.06
    Activations Density 0.026%

    No Known Activations