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. 11-RESID-POST-AA
    6. 91371
    Prev
    Next
    INDEX
    Explanations

    f

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on subword fragments of longer, morphologically complex words—particularly on affix or multi‐syllabic pieces (e.g. parts of Latin‐derived roots or suffixes).

    oai_token-act-pair · o4-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
     것도
    -0.06
    ;"></
    -0.06
     scream
    -0.06
    krv
    -0.06
    !!!!
    -0.06
    ____________
    -0.06
    庄
    -0.06
     McK
    -0.06
    CREASE
    -0.06
     gymn
    -0.06
    POSITIVE LOGITS
    нуть
    0.07
     Ülke
    0.07
     deed
    0.07
     nitrogen
    0.07
    �
    0.06
     founders
    0.06
    �
    0.06
     spirituality
    0.06
    .HasKey
    0.06
    Ini
    0.06
    Activations Density 0.086%

    No Known Activations