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. 120642
    Prev
    Next
    INDEX
    Explanations

    gun control

    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
    -shop
    -0.07
     Siege
    -0.07
    score
    -0.07
     cấu
    -0.06
     sword
    -0.06
    ave
    -0.06
     رسول
    -0.06
     collapse
    -0.06
    No
    -0.06
     factor
    -0.06
    POSITIVE LOGITS
    _Static
    0.07
    polator
    0.06
    			 
    0.06
    ouz
    0.06
    	as
    0.06
     edilmiş
    0.06
     rusty
    0.06
    strconv
    0.06
    _IMETHOD
    0.06
    _TILE
    0.06
    Activations Density 0.023%

    No Known Activations