© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 2662
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate concern or discontent, particularly in social or communal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -expanded
    -0.16
    stoff
    -0.15
    nos
    -0.14
     schem
    -0.14
    uras
    -0.14
    alers
    -0.14
    Ïģε
    -0.13
    enz
    -0.13
    endale
    -0.13
    à¹ĩà¸Ńà¸ķ
    -0.13
    POSITIVE LOGITS
    /stat
    0.26
     heard
    0.23
     directed
    0.22
     uttered
    0.22
     delivered
    0.20
     spoken
    0.20
     dirig
    0.19
     hur
    0.18
     Heard
    0.18
     aimed
    0.18
    Activations Density 0.281%

    No Known Activations