© 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. 109277
    Prev
    Next
    INDEX
    Explanations

    ripe

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases describing fruit ripeness or maturity (e.g., “ripe,” “soft,” “yellow,” “ripening”).

    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
     �
    -0.07
    _stderr
    -0.07
     Playboy
    -0.07
    )!
    -0.06
    背
    -0.06
    泊
    -0.06
     Esc
    -0.06
     circum
    -0.06
     SizedBox
    -0.06
     Plaza
    -0.06
    POSITIVE LOGITS
     ripe
    0.10
    _rg
    0.07
     (::
    0.06
     opsiyon
    0.06
     supplemented
    0.06
     tí
    0.06
     Đ
    0.06
     adolescence
    0.06
    ,其中
    0.06
    __),
    0.06
    Activations Density 0.003%

    No Known Activations