© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 23034
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate concern or reference to legal and ethical issues

    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
    olt
    -0.16
    nes
    -0.15
    oret
    -0.15
    åĴ²
    -0.14
    whatever
    -0.14
    soever
    -0.14
    OLT
    -0.14
    yang
    -0.14
    rement
    -0.14
    à¥Īन
    -0.14
    POSITIVE LOGITS
     impending
    0.37
     imminent
    0.33
     upcoming
    0.29
     forthcoming
    0.27
     how
    0.26
     existence
    0.26
     pending
    0.24
     plans
    0.22
     having
    0.22
     why
    0.21
    Activations Density 0.183%

    No Known Activations