© 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. 25-LLAMASCOPE-RES-32K
    6. 22896
    Prev
    Next
    INDEX
    Explanations

    mentions of sugar, whether in a negative context (sugar-free) or referring to its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orial
    -0.17
    RLF
    -0.16
    eh
    -0.15
    .dds
    -0.15
    .dtd
    -0.15
    sa
    -0.15
    sing
    -0.15
    sel
    -0.15
    mgr
    -0.15
    ek
    -0.14
    POSITIVE LOGITS
     cane
    0.26
    coat
    0.26
    CRM
    0.23
    crm
    0.23
    Cube
    0.19
     refin
    0.19
    imoto
    0.18
    å°¿
    0.18
     Zucker
    0.18
     daddy
    0.18
    Activations Density 0.009%

    No Known Activations