© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25672
    Prev
    Next
    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash

    references to movies and their critiques.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ange
    -0.07
    dna
    -0.07
     thiếu
    -0.07
    portal
    -0.06
    _INST
    -0.06
    нина
    -0.06
     historically
    -0.06
    billing
    -0.06
    коз
    -0.06
     harbour
    -0.06
    POSITIVE LOGITS
     slated
    0.07
     एल
    0.06
     sincerely
    0.06
    XT
    0.06
                    
    0.06
    ql
    0.06
     meal
    0.06
     crem
    0.06
     đó
    0.06
     modelBuilder
    0.06
    Activations Density 0.042%

    No Known Activations