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. 7-RESID-POST-AA
    6. 93576
    Prev
    Next
    INDEX
    Explanations

    A

    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_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
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.07
     مطرح
    -0.07
    首
    -0.07
     blocking
    -0.07
     jade
    -0.06
     Cush
    -0.06
     glEnd
    -0.06
    "\↵
    -0.06
    イド
    -0.06
    /pp
    -0.06
    POSITIVE LOGITS
     ARP
    0.07
     mediocre
    0.06
    PCI
    0.06
    Cities
    0.06
    -stack
    0.06
     Applied
    0.06
    -native
    0.06
    بة
    0.06
     lokal
    0.05
     км
    0.05
    Activations Density 0.000%

    No Known Activations