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. 27203
    Prev
    Next
    INDEX
    Explanations

    to and

    np_max-act · gemini-2.0-flash

    The neuron activates specifically on numeric tokens containing decimal points (i.e. floating-point 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
     parcel
    -0.06
     Del
    -0.06
    Compar
    -0.06
    Æ
    -0.06
    _appro
    -0.06
    Suc
    -0.06
    Insp
    -0.06
    -speaking
    -0.06
    UFACT
    -0.06
     mosquitoes
    -0.06
    POSITIVE LOGITS
    олос
    0.07
    clare
    0.07
     �
    0.07
    @Table
    0.07
    '),↵↵
    0.07
     contentious
    0.06
     tinh
    0.06
    ensation
    0.06
    },
    ↵
    ↵
    0.06
     čtyři
    0.06
    Activations Density 0.011%

    No Known Activations