© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12570
    Prev
    Next
    INDEX
    Explanations

    chemical compounds

    np_max-act · gemini-2.0-flash

    This neuron detects numerical stoichiometric values in chemical formulas, especially decimal concentrations of elements (e.g., Ga₀.₅₃, In content).

    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
     fungus
    -0.06
     UCHAR
    -0.06
     PROFILE
    -0.06
     beginner
    -0.06
    irting
    -0.06
     dine
    -0.06
    Java
    -0.06
    CTRL
    -0.06
    ILTER
    -0.06
     profound
    -0.06
    POSITIVE LOGITS
    .super
    0.08
     ''
    0.07
    (Map
    0.06
    xEC
    0.06
    _payments
    0.06
    538
    0.06
    ////////
    0.06
    _cred
    0.06
     بهره
    0.06
    _View
    0.06
    Activations Density 0.007%

    No Known Activations