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. 31-LLAMASCOPE-RES-32K
    6. 18368
    Prev
    Next
    INDEX
    Explanations

    connections between personal identity and cultural narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĥĩ
    -0.14
    anggan
    -0.13
    YLES
    -0.13
     สล
    -0.13
    çĮ®
    -0.13
    inned
    -0.13
     Kurul
    -0.13
    ãĥ³ãĤ°ãĥ«
    -0.13
    .SDK
    -0.12
    Forgery
    -0.12
    POSITIVE LOGITS
     ner
    0.30
     hip
    0.28
     nerd
    0.28
     hipp
    0.27
     douche
    0.26
    hipster
    0.26
     geek
    0.24
     dude
    0.23
     dudes
    0.23
     fucked
    0.23
    Activations Density 0.476%

    No Known Activations