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. 13-LLAMASCOPE-RES-32K
    6. 15680
    Prev
    Next
    INDEX
    Explanations

    references to navigation elements in a webpage structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ataire
    -0.15
    ovice
    -0.15
    inus
    -0.15
    tabpanel
    -0.15
    eck
    -0.15
    ldb
    -0.15
    .styleable
    -0.14
    uml
    -0.14
    rego
    -0.14
    imens
    -0.14
    POSITIVE LOGITS
    ham
    0.14
    ory
    0.14
    orie
    0.14
    ibar
    0.14
     Slice
    0.14
    719
    0.13
    erea
    0.13
    conti
    0.13
     fat
    0.13
     Yam
    0.13
    Activations Density 0.039%

    No Known Activations