© 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. 11-RESID-POST-AA
    11. 100046
    Prev
    Next
    INDEX
    Explanations

    questions

    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_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
    -visible
    -0.07
    난
    -0.06
    Assertions
    -0.06
    uchos
    -0.06
     Kaynak
    -0.06
    aphore
    -0.06
    	bool
    -0.06
     giden
    -0.06
    ho
    -0.06
    64
    -0.06
    POSITIVE LOGITS
    ॰
    0.07
    во
    0.06
    บาท
    0.06
    __(*
    0.06
    isson
    0.06
    .pid
    0.06
    .mixer
    0.06
    لمه
    0.06
     prov
    0.06
     sinon
    0.06
    Activations Density 0.113%

    No Known Activations