© 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. 19-RESID-POST-AA
    11. 127096
    Prev
    Next
    INDEX
    Explanations

    web page descriptions

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ัตร
    -0.07
     зал
    -0.07
    	menu
    -0.07
     Estimates
    -0.06
     Counter
    -0.06
     hb
    -0.06
     specs
    -0.06
    	password
    -0.06
     imagine
    -0.06
     introduces
    -0.06
    POSITIVE LOGITS
    _PREF
    0.07
     TRAIN
    0.07
    885
    0.06
    pert
    0.06
    '''↵↵
    0.06
    entreprise
    0.06
    IONS
    0.06
    ök
    0.06
     OnPropertyChanged
    0.06
    trag
    0.06
    Activations Density 0.047%

    No Known Activations