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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 16-LLAMASCOPE-RES-32K
    11. 5890
    Prev
    Next
    INDEX
    Explanations

    phrases related to problem-solving and the concept of solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thy
    -0.18
    央
    -0.16
    itable
    -0.15
    .lex
    -0.15
    oba
    -0.15
    rire
    -0.15
    nore
    -0.15
     éģĵ
    -0.15
    lip
    -0.15
    lig
    -0.15
    POSITIVE LOGITS
    æĸ¹æ¡Ī
    0.23
    .solution
    0.21
     solution
    0.19
     solutions
    0.18
     SOLUTION
    0.18
    solution
    0.16
    (solution
    0.16
    ì±ħ
    0.15
     Solution
    0.15
    itary
    0.15
    Activations Density 0.035%

    No Known Activations