© 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. 17-LLAMASCOPE-RES-32K
    11. 31745
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions among people and their challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otlin
    -0.15
    odes
    -0.15
     åĨ
    -0.14
    adel
    -0.14
     RC
    -0.14
    بÙĪر
    -0.14
    inery
    -0.13
    .bz
    -0.13
    dll
    -0.13
    illery
    -0.13
    POSITIVE LOGITS
     indirectly
    0.20
     indirect
    0.18
    ãĤ¯ãĥŃ
    0.18
     aqu
    0.17
    avras
    0.15
    sov
    0.15
    ublic
    0.15
    à¤ľà¤°
    0.15
    aq
    0.15
    æĢ¥
    0.14
    Activations Density 0.002%

    No Known Activations