© 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. 6577
    Prev
    Next
    INDEX
    Explanations

    ranch

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the substring “ranch” (e.g. ranch, rancher, ranching).

    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
     버
    -0.07
    Ol
    -0.07
     вір
    -0.07
    Philip
    -0.07
    David
    -0.07
     EB
    -0.06
    Dar
    -0.06
    #af
    -0.06
     Tele
    -0.06
     elo
    -0.06
    POSITIVE LOGITS
     crunch
    0.09
     Ranch
    0.09
    unch
    0.09
     ranch
    0.08
    retch
    0.08
     Crunch
    0.08
    CH
    0.08
     bunch
    0.08
    UNCH
    0.07
    ign
    0.07
    Activations Density 0.004%

    No Known Activations