Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 120519
    Prev
    Next
    INDEX
    Explanations

    present time

    np_max-act · gemini-2.0-flash

    It detects tokens/phrases that mark the current time or present-tense state (i.e., the writer indicating "right now"/"currently"/"at the moment").

    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
    .throw
    -0.07
    엘
    -0.06
     funeral
    -0.06
    IEnumerator
    -0.06
    НИ
    -0.06
    ו�
    -0.06
     Internal
    -0.06
     witches
    -0.06
    .bool
    -0.06
    icional
    -0.06
    POSITIVE LOGITS
     غير
    0.07
     Lyme
    0.07
    probe
    0.07
    MPI
    0.06
     verbess
    0.06
    lığının
    0.06
     Hội
    0.06
     Nurse
    0.06
    avra
    0.06
     dolore
    0.06
    Activations Density 0.049%

    No Known Activations