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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 80545
    Prev
    Next
    INDEX
    Explanations

    _

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _angles
    -0.07
    Folders
    -0.07
     Snow
    -0.06
    .FileOutputStream
    -0.06
    _thresh
    -0.06
    雑
    -0.06
     Regulatory
    -0.06
     FileStream
    -0.06
    Deserializer
    -0.06
    ForeColor
    -0.06
    POSITIVE LOGITS
            
    ↵        
    ↵
    0.08
     insult
    0.07
     insults
    0.07
    };↵↵
    0.07
    .OR
    0.06
    }↵↵
    0.06
    }↵↵↵
    0.06
    	
    ↵	
    ↵
    0.06
    _mark
    0.06
     flawed
    0.06
    Activations Density 0.037%

    No Known Activations