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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 8485
    Prev
    Next
    INDEX
    Explanations

    key concepts and phrases that imply evaluation and recommendations related to policies and options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    288
    -0.14
    arend
    -0.14
    çĬ
    -0.14
    545
    -0.13
     actually
    -0.13
     aba
    -0.13
    =o
    -0.13
     ÏĥÏĩε
    -0.13
    /pi
    -0.13
    _SCHED
    -0.13
    POSITIVE LOGITS
     solution
    0.29
    solution
    0.26
     Solution
    0.26
    .solution
    0.24
     SOLUTION
    0.23
    _solution
    0.22
     solutions
    0.22
    Solution
    0.22
     alone
    0.21
     Lös
    0.19
    Activations Density 0.007%

    No Known Activations