© 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. 21-LLAMASCOPE-RES-32K
    11. 8106
    Prev
    Next
    INDEX
    Explanations

    terms related to various fields of study and professional qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icode
    -0.19
    ighter
    -0.16
    éĽĦ
    -0.14
    ersonic
    -0.14
    ube
    -0.14
    .Generated
    -0.14
    inned
    -0.14
    اÙģتÙĩ
    -0.14
    ertype
    -0.14
    ÃŃg
    -0.13
    POSITIVE LOGITS
    ology
    0.38
     science
    0.34
    iology
    0.32
     theory
    0.32
     medicine
    0.30
    atology
    0.30
     sciences
    0.29
    istics
    0.29
     psychology
    0.28
    ศาสà¸ķร
    0.27
    Activations Density 0.332%

    No Known Activations