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. 15-RESID-POST-AA
    6. 40636
    Prev
    Next
    INDEX
    Explanations

    Suffixes "ed", "s", "ing"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uch
    -0.06
    	sf
    -0.06
                                                                  
    -0.06
    =model
    -0.06
    	self
    -0.06
     Van
    -0.06
    BX
    -0.06
     smarter
    -0.06
     lobster
    -0.06
    .bot
    -0.06
    POSITIVE LOGITS
    ublice
    0.08
    acs
    0.07
    crafted
    0.07
    Alternate
    0.07
    Κ
    0.06
    anceled
    0.06
    _Width
    0.06
    렀
    0.06
    يم
    0.06
    ladığ
    0.06
    Activations Density 0.213%

    No Known Activations