© 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. 90659
    Prev
    Next
    INDEX
    Explanations

    cost analysis

    np_max-act · gemini-2.0-flash

    The neuron is specialized in picking out economic cost terminology and cost‐effectiveness metrics (e.g. “cost,” “cost‐effectiveness,” “cost per,” monetary values).

    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
    (@"
    -0.07
     aber
    -0.06
     entries
    -0.06
    }:
    -0.06
     ][
    -0.06
    än
    -0.06
     ReturnValue
    -0.06
    onn
    -0.06
    (opts
    -0.06
    856
    -0.06
    POSITIVE LOGITS
     covid
    0.06
     Morm
    0.06
     βά
    0.06
     NEC
    0.06
    bursement
    0.06
     rpm
    0.06
     vigorous
    0.06
    沖
    0.06
    _top
    0.06
    _VM
    0.06
    Activations Density 0.012%

    No Known Activations