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. 6-LLAMASCOPE-RES-32K
    6. 7934
    Prev
    Next
    INDEX
    Explanations

    information related to business entities and their performance, especially in a corporate and investment context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angan
    -0.15
    еÑĤе
    -0.15
    ä½
    -0.15
    ìĺ
    -0.15
    wing
    -0.14
     èĩ³
    -0.14
    elijk
    -0.14
    aml
    -0.14
     Mk
    -0.14
    LOSE
    -0.13
    POSITIVE LOGITS
    /sbin
    0.14
    pok
    0.14
    hic
    0.14
    æĪ·
    0.14
    orting
    0.14
    olist
    0.14
     Zaman
    0.14
    559
    0.14
    ofday
    0.14
     whose
    0.13
    Activations Density 0.224%

    No Known Activations