Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 128840
    Prev
    Next
    INDEX
    Explanations

    wanting attention/love

    np_max-act · gemini-2.0-flash

    attention

    np_max-act · gemini-2.5-flashTriggered by @aardvarkkr
    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
    •my list

    No Comments

    Negative Logits
    orse
    -0.07
     Bản
    -0.07
    jie
    -0.07
    ifiers
    -0.06
     Benson
    -0.06
     Σύ
    -0.06
    ritic
    -0.06
    igsaw
    -0.06
    нию
    -0.06
    795
    -0.06
    POSITIVE LOGITS
     Hof
    0.06
    .deserialize
    0.06
    .ALIGN
    0.06
     Hass
    0.06
     �
    0.06
     переж
    0.06
     Army
    0.06
     tỉ
    0.05
     resumed
    0.05
     respons
    0.05
    Activations Density 0.062%

    No Known Activations