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. 11-RESID-POST-AA
    6. 55044
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on cytokine and immune‐signaling molecule labels (e.g. IL-4, IL-6, IFN-γ, TNF-α).

    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
    .Geometry
    -0.07
    �
    -0.06
     ios
    -0.06
    	byte
    -0.06
     Correction
    -0.06
    -pointer
    -0.06
    _SY
    -0.06
    .numpy
    -0.06
     Pant
    -0.06
    ח
    -0.06
    POSITIVE LOGITS
    .DropDown
    0.08
     Oliveira
    0.07
     hopefully
    0.07
    ี้↵
    0.06
    acing
    0.06
    )</
    0.06
    marine
    0.06
     fulfil
    0.06
    	all
    0.06
    原始
    0.06
    Activations Density 0.045%

    No Known Activations