© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-32K
    6. 25180
    Prev
    Next
    INDEX
    Explanations

    phrases related to division or separation into parts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kal
    -0.15
     Morr
    -0.15
    bote
    -0.15
    emo
    -0.14
    ijd
    -0.14
    abox
    -0.14
    ibraries
    -0.14
     Void
    -0.14
    rett
    -0.14
    bast
    -0.14
    POSITIVE LOGITS
     two
    0.19
    isko
    0.17
     Mit
    0.16
     McD
    0.15
     Mack
    0.15
     three
    0.15
     four
    0.14
    ANS
    0.14
     Highest
    0.14
    ache
    0.14
    Activations Density 0.021%

    No Known Activations