Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 18-LLAMASCOPE-RES-32K
    6. 28824
    Prev
    Next
    INDEX
    Explanations

    structural features and specifications related to slope and angles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     upside
    -0.16
     Mein
    -0.15
    684
    -0.15
    HEMA
    -0.14
    flip
    -0.14
    ODB
    -0.14
     stuck
    -0.13
    uck
    -0.13
     circ
    -0.13
    xing
    -0.13
    POSITIVE LOGITS
     slope
    0.35
    slope
    0.32
     slopes
    0.31
     slo
    0.28
     Slo
    0.28
     gradients
    0.26
     gradient
    0.24
    _slope
    0.24
    åĿ¡
    0.23
     steep
    0.21
    Activations Density 0.113%

    No Known Activations