© 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. 7825
    Prev
    Next
    INDEX
    Explanations

    explaining concepts to someone

    np_max-act · gemini-2.0-flash

    This neuron activates on words specifying the intended audience or listener (e.g. “high school student,” “phd student,” “experienced investor,” “intelligent cat,” “young man”).

    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
     Moose
    -0.08
    LOSS
    -0.07
    ousing
    -0.07
    _SUBJECT
    -0.07
     Targets
    -0.07
     Decode
    -0.07
     CVS
    -0.07
     colours
    -0.06
    Motion
    -0.06
     Valencia
    -0.06
    POSITIVE LOGITS
     Benghazi
    0.08
     regimen
    0.06
     entrenched
    0.06
    InputStream
    0.06
    .AddField
    0.06
    .SelectedIndex
    0.06
     Amir
    0.06
     depressed
    0.06
    рел
    0.06
     Andr
    0.05
    Activations Density 0.036%

    No Known Activations