© 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. 7970
    Prev
    Next
    INDEX
    Explanations

    er

    np_max-act · gemini-2.0-flash

    The neuron specifically detects the subtoken “er” (the common “-er” suffix) in code identifiers.

    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
     говорить
    -0.07
    _>
    -0.07
    oire
    -0.06
    '}}
    -0.06
    SOAP
    -0.06
     نمودار
    -0.06
    _TE
    -0.06
    KeyPress
    -0.06
    �
    -0.06
    执
    -0.06
    POSITIVE LOGITS
    loating
    0.07
    floating
    0.06
    ex
    0.06
     invented
    0.06
    рост
    0.06
     OST
    0.06
    roads
    0.06
    _az
    0.06
     VG
    0.06
    asted
    0.06
    Activations Density 0.002%

    No Known Activations