© 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
    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. 126683
    Prev
    Next
    INDEX
    Explanations

    Hedgehogs and porcupines

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of porcupines and their quills—i.e. the word “porcupine” (subword “porcup”) and related quill-spike terms.

    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
    .Logf
    -0.07
    �
    -0.07
    すべて
    -0.06
    Level
    -0.06
    .algorithm
    -0.06
     halftime
    -0.06
    olang
    -0.06
     situated
    -0.06
     defeating
    -0.06
                        
    -0.06
    POSITIVE LOGITS
     GFP
    0.07
    .InnerException
    0.07
     Pompe
    0.06
    -text
    0.06
    aguay
    0.06
     시험
    0.06
    inium
    0.06
     textured
    0.06
    illum
    0.06
    込み
    0.06
    Activations Density 0.004%

    No Known Activations