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. 23-RESID-POST-AA
    6. 40669
    Prev
    Next
    INDEX
    Explanations

    recognition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     total
    -0.07
     Combined
    -0.07
     lowered
    -0.07
     posterior
    -0.07
    -object
    -0.07
    _corpus
    -0.07
     eastern
    -0.07
    582
    -0.07
     aimed
    -0.06
     Trees
    -0.06
    POSITIVE LOGITS
     recognizing
    0.12
     recognize
    0.11
     recognizes
    0.11
     recognized
    0.10
     Recogn
    0.09
     recognizer
    0.09
     recognise
    0.09
    зн
    0.08
     recogn
    0.07
     recognised
    0.07
    Activations Density 0.023%

    No Known Activations