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. 19012
    Prev
    Next
    INDEX
    Explanations

    combustion

    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
     WORD
    -0.07
     trick
    -0.07
     spear
    -0.06
    IODevice
    -0.06
    Arn
    -0.06
    άλι
    -0.06
    -Key
    -0.06
    roken
    -0.06
     fear
    -0.06
     parl
    -0.06
    POSITIVE LOGITS
     combustion
    0.16
     combust
    0.10
    олж
    0.07
    		    	
    0.07
     Ensemble
    0.07
    柴
    0.07
    Carbon
    0.07
    ابعة
    0.07
     pulmonary
    0.07
     USB
    0.07
    Activations Density 0.002%

    No Known Activations