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. 15-RESID-POST-AA
    6. 988
    Prev
    Next
    INDEX
    Explanations

    agent

    np_max-act · gemini-2.0-flash

    tokens representing numeric values, monetary amounts, quantities, and time units (numbers, $/NRE, thousands, weeks, etc.).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _alg
    -0.07
    Toolkit
    -0.07
    rowned
    -0.06
    *log
    -0.06
    งแต
    -0.06
    _ut
    -0.06
    NSS
    -0.06
     �
    -0.06
     dictionaries
    -0.06
     Antib
    -0.06
    POSITIVE LOGITS
    anos
    0.07
    عان
    0.07
    andro
    0.07
    4
    0.07
    ويك
    0.07
     процессе
    0.07
    ѕ
    0.07
     mír
    0.07
     nabíd
    0.06
    5
    0.06
    Activations Density 19.064%

    No Known Activations