Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8467
    Prev
    Next
    INDEX
    Explanations

    deciding

    np_max-act · gemini-2.0-flash

    The neuron detects numerical tokens representing floating-point activation or measurement values (i.e. numbers with decimal fractions).

    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
     모습
    -0.06
     기술
    -0.06
    istics
    -0.05
     См
    -0.05
    atem
    -0.05
     commune
    -0.05
     defend
    -0.05
    _meter
    -0.05
     siege
    -0.05
     Drama
    -0.05
    POSITIVE LOGITS
     striking
    0.07
    -cn
    0.07
    /application
    0.07
    Creators
    0.07
    ORG
    0.07
     flashy
    0.07
    	org
    0.07
    ">'↵
    0.06
    _UnityEngine
    0.06
     ιστο
    0.06
    Activations Density 0.031%

    No Known Activations