© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41442
    Prev
    Next
    INDEX
    Explanations

    previously

    np_max-act · gemini-2.0-flash

    The neuron fires on adverbial or adjectival tokens that mark prior or earlier states—words like “previously,” “formerly,” and similar temporal modifiers.

    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
     род
    -0.07
     �
    -0.07
     syscall
    -0.07
    ос
    -0.07
     Boss
    -0.06
    壓
    -0.06
     edm
    -0.06
    icing
    -0.06
    Mind
    -0.06
     Mom
    -0.06
    POSITIVE LOGITS
     previously
    0.14
     Previously
    0.09
    Previously
    0.09
     раніше
    0.07
    ovně
    0.07
     draped
    0.07
    .SpringBootApplication
    0.07
    /*================================================================
    0.07
    IFIED
    0.07
     dříve
    0.07
    Activations Density 0.008%

    No Known Activations