© 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. 36879
    Prev
    Next
    INDEX
    Explanations

    comes

    np_max-act · gemini-2.0-flash

    tweets related to war or conflict.

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

    The neuron strongly fires on the subword “error” (e.g. in “/Terror” or as the standalone token “error”).

    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
    PLIC
    -0.07
    textContent
    -0.07
    BOSE
    -0.06
    ��이
    -0.06
    @JsonProperty
    -0.06
    radan
    -0.06
    _COUNT
    -0.06
    ήλ
    -0.06
    dropIfExists
    -0.06
    -President
    -0.06
    POSITIVE LOGITS
     bloque
    0.07
     mins
    0.07
     선택
    0.06
     enquiry
    0.06
     bars
    0.06
     NSRange
    0.06
    !"
    0.06
    Low
    0.06
    ніч
    0.06
    Remove
    0.06
    Activations Density 0.000%

    No Known Activations