© 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
    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. 77702
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    relationships involving body image and lifestyle choices.

    oai_token-act-pair · gpt-4o-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
     And
    -0.11
     and
    -0.11
     AND
    -0.10
    and
    -0.09
    (and
    -0.09
    _and
    -0.08
    And
    -0.08
     but
    -0.08
    -and
    -0.08
    "But
    -0.08
    POSITIVE LOGITS
    _SZ
    0.06
    _CATEGORY
    0.06
    _NODE
    0.06
    VA
    0.06
    _UDP
    0.06
     thin
    0.06
     setUsername
    0.06
    ],$
    0.06
    esium
    0.06
    	pc
    0.06
    Activations Density 0.053%

    No Known Activations