© 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. 126068
    Prev
    Next
    INDEX
    Explanations

    something

    np_max-act · gemini-2.0-flash

    The neuron fires on the phrase “something that.”

    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
    		↵		↵
    -0.09
    ak
    -0.06
    _MAP
    -0.06
    	↵	↵
    -0.06
    .getHost
    -0.06
    				↵				↵
    -0.06
     decir
    -0.06
    TRANS
    -0.05
    	try
    -0.05
    (de
    -0.05
    POSITIVE LOGITS
     willingness
    0.08
     муль
    0.07
    ARATION
    0.07
     Something
    0.07
     Samantha
    0.07
     욕
    0.07
    -sp
    0.07
     ries
    0.07
     something
    0.07
     ödem
    0.07
    Activations Density 0.025%

    No Known Activations