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. 15-RESID-POST-AA
    6. 21082
    Prev
    Next
    INDEX
    Explanations

    Descriptions of people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coef
    -0.07
    forcement
    -0.06
     alive
    -0.06
     stacked
    -0.06
     cob
    -0.06
    	virtual
    -0.06
     (@
    -0.06
    Ư�
    -0.06
     çap
    -0.06
     nostra
    -0.06
    POSITIVE LOGITS
    :init
    0.06
    Results
    0.06
    }});↵
    0.06
     έχουν
    0.06
    ']}'
    0.06
     searchData
    0.06
    を見
    0.06
    ')}}">
    0.06
    cookie
    0.06
    _template
    0.06
    Activations Density 0.052%

    No Known Activations