Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 18356
    Prev
    Next
    INDEX
    Explanations

    phrases related to job responsibilities and tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Contours
    -0.17
    ponsored
    -0.15
    Attach
    -0.15
     supervise
    -0.14
     sponsoring
    -0.14
    ÙĪØ§Øª
    -0.14
    endoza
    -0.14
    achi
    -0.14
    Orm
    -0.13
     financed
    -0.13
    POSITIVE LOGITS
     handle
    0.22
    lia
    0.22
     deal
    0.21
     manage
    0.20
     research
    0.20
     answer
    0.20
     assist
    0.20
     manages
    0.20
     prepare
    0.19
     handles
    0.19
    Activations Density 0.377%

    No Known Activations