© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15088
    Prev
    Next
    INDEX
    Explanations

    variations of the word "protect" or related words indicating safeguarding or preservation

    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
    ÌĤ
    -0.17
    ittal
    -0.16
    uate
    -0.16
    ió
    -0.15
     Blo
    -0.15
    isia
    -0.15
    885
    -0.15
    mitters
    -0.14
    _STRIP
    -0.14
    iar
    -0.14
    POSITIVE LOGITS
     prot
    0.28
    ector
    0.25
     Prot
    0.24
    otypical
    0.24
    ocols
    0.23
    otyping
    0.22
    ég
    0.22
    uber
    0.21
    екÑĤоÑĢ
    0.20
    folio
    0.20
    Activations Density 0.010%

    No Known Activations