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. 23-LLAMASCOPE-RES-32K
    6. 30728
    Prev
    Next
    INDEX
    Explanations

    JavaScript and jQuery-related code elements and their structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asticsearch
    -0.26
    enticate
    -0.25
    DebugEnabled
    -0.24
    irtual
    -0.22
    olume
    -0.22
    outube
    -0.21
    ighbors
    -0.21
    riteln
    -0.21
    gorithm
    -0.20
    ernel
    -0.20
    POSITIVE LOGITS
    ï¸ı
    0.19
    er
    0.18
    erin
    0.17
    ï¸
    0.16
    errupted
    0.15
    eria
    0.15
    ASN
    0.15
    935
    0.14
     Roberts
    0.14
     Hacker
    0.14
    Activations Density 0.112%

    No Known Activations