© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 85820
    Prev
    Next
    INDEX
    Explanations

    whatsoever

    np_max-act · gemini-2.0-flash

    The neuron consistently fires on the word “whatsoever” in software‐license disclaimer text.

    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
    　ﾞ
    -0.07
    .ObjectModel
    -0.07
    UniformLocation
    -0.07
     počtu
    -0.07
    .WinForms
    -0.06
     lesbisk
    -0.06
    serde
    -0.06
    }
↵
↵
↵
↵
    -0.06
     INLINE
    -0.06
     little
    -0.06
    POSITIVE LOGITS
     WHATSOEVER
    0.08
    沃
    0.08
     whatsoever
    0.08
     contemplated
    0.08
    谱
    0.07
     seeking
    0.07
    Research
    0.07
     øns
    0.07
    VEL
    0.07
     personnel
    0.06
    Activations Density 0.001%

    No Known Activations