© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89826
    Prev
    Next
    INDEX
    Explanations

    -channel

    np_max-act · gemini-2.0-flash

    This neuron specifically activates on mentions of MOSFET transistors and their channel or device identifiers (e.g., “MN11,” “MP12,” “p-channel MOS,” “NMOS,” etc.).

    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
    _sigma
    -0.07
    riteria
    -0.07
    .isRequired
    -0.06
    EMPTY
    -0.06
    aciente
    -0.06
     solids
    -0.06
     Mec
    -0.06
    .pyplot
    -0.06
    ce
    -0.06
    ?>>
    -0.06
    POSITIVE LOGITS
     ALLOW
    0.07
     Caf
    0.07
     instructional
    0.07
    VERTISEMENT
    0.07
     Collabor
    0.06
    Plain
    0.06
    AbsolutePath
    0.06
     Atomic
    0.06
     Cleaning
    0.06
     Cement
    0.06
    Activations Density 0.002%

    No Known Activations