© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12593
    Prev
    Next
    INDEX
    Explanations

    adherence

    np_max-act · gemini-2.0-flash

    The neuron is detecting occurrences of the word “adherence” (and its close variants).

    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
    _requested
    -0.07
    .bill
    -0.07
     gospel
    -0.07
    Royal
    -0.07
    British
    -0.07
     KING
    -0.07
     quitting
    -0.06
    ()>
    -0.06
     guilt
    -0.06
     profitable
    -0.06
    POSITIVE LOGITS
     adher
    0.12
     adhere
    0.11
     adherence
    0.10
     Adler
    0.08
    依
    0.08
    ENCE
    0.07
    herence
    0.07
     inher
    0.07
    uden
    0.07
    hr
    0.07
    Activations Density 0.007%

    No Known Activations