© 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. 15-LLAMASCOPE-RES-32K
    6. 23491
    Prev
    Next
    INDEX
    Explanations

    conversations about personal experiences and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azor
    -0.17
    sdale
    -0.16
    ugo
    -0.15
     exercitation
    -0.15
    rang
    -0.15
    CTYPE
    -0.14
    \Blueprint
    -0.14
    .SetParent
    -0.14
    rift
    -0.14
    Å¡nÃŃ
    -0.14
    POSITIVE LOGITS
     somehow
    0.28
     Somehow
    0.21
     feat
    0.21
     ability
    0.19
     miracle
    0.19
     remarkable
    0.19
     surv
    0.18
     mirac
    0.18
     resilience
    0.18
     amazing
    0.18
    Activations Density 0.231%

    No Known Activations