© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 26487
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research and its societal impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opoulos
    -0.15
     Reb
    -0.15
    roupe
    -0.15
    ÑĢоÑģ
    -0.15
    ODO
    -0.14
     Barg
    -0.14
    rosse
    -0.14
    adow
    -0.13
    opes
    -0.13
    tero
    -0.13
    POSITIVE LOGITS
     commercial
    0.22
     outputs
    0.21
     translation
    0.20
     Commercial
    0.19
     transfer
    0.19
     Outputs
    0.19
    Commercial
    0.19
    -commercial
    0.19
    outputs
    0.18
     transl
    0.18
    Activations Density 0.077%

    No Known Activations