© 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
    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. 43408
    Prev
    Next
    INDEX
    Explanations

    Y

    np_max-act · gemini-2.0-flash

    This neuron detects Russian inflectional morpheme segments (affix parts of conjugated or declined words).

    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
    奶
    -0.07
    eng
    -0.07
     Achilles
    -0.07
    smooth
    -0.07
    特別
    -0.07
    [Test
    -0.07
    _areas
    -0.07
     echoed
    -0.07
    }}
    -0.07
     Rita
    -0.06
    POSITIVE LOGITS
    ?\
    0.06
    �
    0.06
     hotels
    0.06
    adf
    0.06
    alto
    0.06
    ัดการ
    0.06
     Прав
    0.06
     ^{°}
    0.05
    님
    0.05
    (withId
    0.05
    Activations Density 0.000%

    No Known Activations