© 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. 7-LLAMASCOPE-RES-32K
    11. 13437
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to combinations and collaborative efforts in processes or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arih
    -0.15
    Loader
    -0.15
     Uniform
    -0.14
    pher
    -0.14
    soever
    -0.14
    aha
    -0.13
    RootElement
    -0.13
    Та
    -0.13
    Tot
    -0.13
     Laundry
    -0.13
    POSITIVE LOGITS
    ÑĥÑĢÑĥ
    0.17
     combination
    0.16
    spell
    0.16
    isphere
    0.15
    ienie
    0.15
     together
    0.15
     bÃło
    0.15
    strup
    0.15
    eck
    0.14
    529
    0.14
    Activations Density 0.209%

    No Known Activations