© 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. 27-LLAMASCOPE-RES-32K
    11. 5676
    Prev
    Next
    INDEX
    Explanations

    references to specific topics or entities, particularly those beginning with the letter "p."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ower
    -0.16
    HAS
    -0.15
    ÇIJ
    -0.15
    ожд
    -0.14
     calend
    -0.14
    leet
    -0.14
    orns
    -0.14
    alnız
    -0.14
    redo
    -0.14
    owers
    -0.14
    POSITIVE LOGITS
    incipal
    0.15
    reesome
    0.15
    /licenses
    0.15
    oble
    0.15
    Jobs
    0.14
     worst
    0.14
    ape
    0.14
    æĬ±
    0.14
    oca
    0.14
    ervers
    0.14
    Activations Density 0.022%

    No Known Activations