© 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. 7258
    Prev
    Next
    INDEX
    Explanations

    words related to issues, problems, and questions in various contexts

    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
    figcaption
    -0.16
    ÑĦи
    -0.15
    ãĥ¼ãĥĪ
    -0.15
     Web
    -0.14
    NE
    -0.14
    rx
    -0.14
    uh
    -0.13
    è¾ŀ
    -0.13
    variant
    -0.13
    Ø®Ùħ
    -0.13
    POSITIVE LOGITS
    .ht
    0.18
    -Ta
    0.16
    ClientRect
    0.15
    652
    0.15
    .ta
    0.14
    668
    0.14
    oins
    0.14
    948
    0.14
    odal
    0.14
    upil
    0.14
    Activations Density 0.123%

    No Known Activations