© 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. 90958
    Prev
    Next
    INDEX
    Explanations

    ymb

    np_max-act · gemini-2.0-flash

    The neuron fires on the literal bracketed prompt “[Ready],” i.e. the sequence of tokens “[”, “Ready”, “]”.

    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
    ्वत
    -0.06
     Categories
    -0.06
    ぁ
    -0.06
    esiz
    -0.06
    /md
    -0.06
    že
    -0.06
     edilmiştir
    -0.06
     Hanna
    -0.06
     CTL
    -0.06
    visa
    -0.06
    POSITIVE LOGITS
    <Any
    0.07
     bedside
    0.06
     Tomorrow
    0.06
     congregation
    0.06
     congreg
    0.06
    865
    0.06
     undef
    0.06
     investigations
    0.06
    (point
    0.06
    �
    0.06
    Activations Density 0.002%

    No Known Activations