© 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. 580
    Prev
    Next
    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash

    The neuron activates on words that signal a conclusion or final summary (e.g. “final,” “finally,” “end”).

    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
    (u
    -0.06
     etki
    -0.06
     _{
    -0.06
    سین
    -0.06
     occupy
    -0.06
     demokrat
    -0.06
     Siber
    -0.06
    (pointer
    -0.06
     Unsafe
    -0.06
     Hue
    -0.06
    POSITIVE LOGITS
     final
    0.08
     �
    0.07
    final
    0.07
    _FINISH
    0.07
     end
    0.06
    Final
    0.06
     ω
    0.06
     ComponentFixture
    0.06
    	final
    0.06
    rganization
    0.06
    Activations Density 0.033%

    No Known Activations