© 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. 28-LLAMASCOPE-RES-32K
    6. 877
    Prev
    Next
    INDEX
    Explanations

    terms related to patient information and confidentiality in a medical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rett
    -0.15
    662
    -0.15
    lients
    -0.15
    -associated
    -0.15
    liÄį
    -0.14
    fak
    -0.14
    rah
    -0.14
    574
    -0.14
    缮ãģ®
    -0.14
    edb
    -0.13
    POSITIVE LOGITS
     combo
    0.30
     relationship
    0.30
     ratio
    0.27
     combination
    0.26
     relation
    0.25
     combos
    0.24
     Ratio
    0.24
     interface
    0.24
     Relationship
    0.24
     axis
    0.24
    Activations Density 0.190%

    No Known Activations