© 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. 42603
    Prev
    Next
    INDEX
    Explanations

    file trees

    np_max-act · gemini-2.0-flash

    The neuron activates on inline code markers in documentation or Markdown (the backtick-delimited filenames and code snippets).

    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
    chemical
    -0.06
     
    -0.06
     bàn
    -0.06
    Bearer
    -0.06
    こそ
    -0.06
     wholesome
    -0.06
    och
    -0.06
    LED
    -0.06
    .Flags
    -0.06
     vaz
    -0.06
    POSITIVE LOGITS
    (gameObject
    0.06
    이라
    0.06
     Cached
    0.06
    blocking
    0.06
    �
    0.06
     intimid
    0.06
    isdigit
    0.05
    (distance
    0.05
    (rx
    0.05
    	lp
    0.05
    Activations Density 0.012%

    No Known Activations