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. 9-LLAMASCOPE-RES-32K
    6. 3692
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases that indicate important locations, solutions, and relationships within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olt
    -0.15
    ella
    -0.15
    оÑĩкÑĥ
    -0.14
    ouis
    -0.14
    abr
    -0.14
    ORIA
    -0.14
    åħ¶ä¸Ń
    -0.13
    065
    -0.13
    alic
    -0.13
    allet
    -0.13
    POSITIVE LOGITS
    romatic
    0.15
    ÙĬØ©
    0.14
    iest
    0.14
    ufe
    0.14
    زÙĪ
    0.14
    _taxonomy
    0.13
    ipt
    0.13
    neys
    0.13
    HQ
    0.13
    590
    0.13
    Activations Density 0.177%

    No Known Activations