© 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. 3-LLAMASCOPE-RES-32K
    11. 23438
    Prev
    Next
    INDEX
    Explanations

    the term "dedicated" in various contexts, indicating a focus on commitment or specialized services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.18
    stras
    -0.15
    afort
    -0.15
    YT
    -0.15
    éal
    -0.14
    leigh
    -0.14
    okin
    -0.14
     Strait
    -0.14
    yer
    -0.14
    aine
    -0.13
    POSITIVE LOGITS
    ded
    0.20
    rix
    0.16
    groups
    0.15
     Ded
    0.14
    алеж
    0.14
    vailable
    0.14
    pletion
    0.13
     æ¢
    0.13
    apse
    0.13
    ized
    0.13
    Activations Density 0.010%

    No Known Activations