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. 126920
    Prev
    Next
    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash

    discussions about political figures and their impact on social issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron primarily fires on verbs and verb-like auxiliaries (including negations) that signal actions, plans, or changes in state.

    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
    oders
    -0.07
     underground
    -0.07
    aturity
    -0.06
    warning
    -0.06
     нек
    -0.06
     Miy
    -0.06
     buggy
    -0.06
    isc
    -0.06
     otp
    -0.06
     publicly
    -0.06
    POSITIVE LOGITS
    ChartData
    0.07
    =<?
    0.06
    ременно
    0.06
    .nii
    0.06
    肖
    0.06
    ]').
    0.06
    =localhost
    0.06
     которое
    0.06
    .flags
    0.06
     yyn
    0.06
    Activations Density 0.305%

    No Known Activations