Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 21229
    Prev
    Next
    INDEX
    Explanations

    transition

    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
    Server
    -0.07
    _CANCEL
    -0.07
    耳
    -0.06
    	mat
    -0.06
    	ArrayList
    -0.06
     wor
    -0.06
    /**
    -0.06
    (R
    -0.06
    \u
    -0.06
    NSArray
    -0.06
    POSITIVE LOGITS
     transition
    0.13
     Transition
    0.11
    transition
    0.09
     transitions
    0.09
     transitioning
    0.08
     interim
    0.08
    icopt
    0.07
    ione
    0.07
     simultaneously
    0.07
    ció
    0.07
    Activations Density 0.008%

    No Known Activations