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. 21-LLAMASCOPE-RES-32K
    6. 15724
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as parentheses and curly brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stown
    -0.17
    Unified
    -0.15
    etler
    -0.15
    stances
    -0.15
     Unified
    -0.15
    ecn
    -0.14
    stance
    -0.14
    arry
    -0.14
    GetCurrent
    -0.14
    throp
    -0.14
    POSITIVE LOGITS
     self
    0.31
    	self
    0.23
    self
    0.23
    (self
    0.22
    [self
    0.22
    -self
    0.22
    =self
    0.21
     this
    0.21
    	this
    0.20
    (this
    0.19
    Activations Density 0.006%

    No Known Activations