© 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. 11-LLAMASCOPE-RES-32K
    11. 6929
    Prev
    Next
    INDEX
    Explanations

    references to emissions reduction targets and future projections related to climate goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agli
    -0.16
    ãĥ¼ãĥ©
    -0.15
    enge
    -0.14
    vu
    -0.14
    .Html
    -0.14
    nown
    -0.14
    aked
    -0.14
     اختÛĮار
    -0.14
     Begin
    -0.14
    oun
    -0.14
    POSITIVE LOGITS
     asc
    0.15
     bi
    0.15
    asz
    0.14
    uD
    0.14
    assy
    0.14
    oir
    0.14
    ienne
    0.14
    ons
    0.14
     Chall
    0.14
    Branch
    0.13
    Activations Density 0.022%

    No Known Activations