© 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. 2-LLAMASCOPE-RES-32K
    11. 31977
    Prev
    Next
    INDEX
    Explanations

    contexts related to dependence or reliance, particularly on resources or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abit
    -0.15
    reative
    -0.14
    ysz
    -0.14
    terr
    -0.14
    hani
    -0.14
    conti
    -0.14
    ynom
    -0.14
    álo
    -0.13
    phia
    -0.13
     mash
    -0.13
    POSITIVE LOGITS
    INO
    0.15
    kits
    0.15
    enger
    0.15
    неÑĢ
    0.15
    ToOne
    0.14
    amedi
    0.14
    heed
    0.13
    orsk
    0.13
    183
    0.13
    _Ent
    0.13
    Activations Density 0.004%

    No Known Activations