© 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. 6559
    Prev
    Next
    INDEX
    Explanations

    forever

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the word “forever,” i.e. it detects occurrences of the token forever.

    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
     cases
    -0.08
     sample
    -0.08
     niche
    -0.08
    タ
    -0.08
     cylindrical
    -0.07
     respondents
    -0.07
     sixth
    -0.07
     negative
    -0.07
     slit
    -0.07
     Technique
    -0.07
    POSITIVE LOGITS
     forever
    0.13
     Forever
    0.12
     永
    0.09
    Forever
    0.09
    _Success
    0.07
    ้องก
    0.07
    唯
    0.07
    clair
    0.06
     Гер
    0.06
    財
    0.06
    Activations Density 0.004%

    No Known Activations