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. 11-RESID-POST-AA
    6. 92765
    Prev
    Next
    INDEX
    Explanations

    confluence

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of cell culture growth conditions, especially confluent or grown cells.

    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
     crc
    -0.07
    'M
    -0.07
     etti
    -0.06
    _z
    -0.06
     boğ
    -0.06
    966
    -0.06
     nonzero
    -0.06
     butter
    -0.06
     spikes
    -0.06
    060
    -0.06
    POSITIVE LOGITS
    complexContent
    0.06
    redit
    0.06
    και
    0.06
     IHttp
    0.06
     Ghost
    0.06
    (ii
    0.06
    ("'"
    0.06
    .margin
    0.06
    availability
    0.06
    <|eom_id|>
    0.06
    Activations Density 0.014%

    No Known Activations