© 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. 126143
    Prev
    Next
    INDEX
    Explanations

    phase of

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of project or development “phases,” i.e. the word “phase” when numbering or describing stages.

    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
    (parts
    -0.06
     těl
    -0.06
     gays
    -0.06
    .Ok
    -0.06
     Perry
    -0.06
     회사
    -0.06
    HN
    -0.06
     term
    -0.06
    .Mutable
    -0.06
    primary
    -0.06
    POSITIVE LOGITS
     unreachable
    0.07
          
    0.06
    #!/
    0.06
    .clips
    0.06
    .tagName
    0.06
    ยว
    0.06
     çeşit
    0.06
     Albums
    0.06
     civilizations
    0.06
    .Compile
    0.06
    Activations Density 0.013%

    No Known Activations