© 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. 29-LLAMASCOPE-RES-32K
    6. 17113
    Prev
    Next
    INDEX
    Explanations

    expressions of positive sentiment and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agan
    -0.14
     unforgettable
    -0.14
    ollar
    -0.13
    è¨Ģãģ£ãģŁ
    -0.13
     unfavor
    -0.13
     astonished
    -0.13
    íļ¨
    -0.13
    achten
    -0.13
    Argb
    -0.13
    olid
    -0.12
    POSITIVE LOGITS
     nice
    0.38
     heart
    0.31
    nice
    0.29
    Nice
    0.28
     grat
    0.28
     Nice
    0.27
     great
    0.26
     pleasing
    0.26
     encouraging
    0.26
     neat
    0.24
    Activations Density 0.146%

    No Known Activations