© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 121681
    Prev
    Next
    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     funktion
    -0.06
    ergy
    -0.06
    ufe
    -0.06
     внутри
    -0.06
    으니
    -0.06
    Waiting
    -0.06
    血
    -0.06
    IMP
    -0.06
    (ok
    -0.06
    Suc
    -0.06
    POSITIVE LOGITS
    ]]↵
    0.07
     sur
    0.06
     surrogate
    0.06
     ArgumentException
    0.06
    .tracks
    0.06
    constructed
    0.06
    toi
    0.06
    measurement
    0.06
     ]↵↵
    0.06
    .assignment
    0.06
    Activations Density 0.002%

    No Known Activations