© 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. 25335
    Prev
    Next
    INDEX
    Explanations

    Akt

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find mentions of the Akt kinase in PI3K/Akt signaling contexts.

    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
    ereo
    -0.07
     RoundedRectangle
    -0.07
     unforgettable
    -0.07
    Semaphore
    -0.07
    ชม
    -0.07
    beam
    -0.06
     Clip
    -0.06
    arena
    -0.06
    forgettable
    -0.06
    eroon
    -0.06
    POSITIVE LOGITS
    Akt
    0.09
     Akt
    0.08
    故
    0.07
     proud
    0.07
     STAT
    0.06
     Kafka
    0.06
    /pr
    0.06
     recently
    0.06
     JUST
    0.06
     Auckland
    0.06
    Activations Density 0.001%

    No Known Activations