© 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. 31-LLAMASCOPE-RES-32K
    11. 6412
    Prev
    Next
    INDEX
    Explanations

    specific financial and contractual terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pest
    -0.17
    λει
    -0.16
    aco
    -0.16
    azine
    -0.15
    ACHE
    -0.15
    azon
    -0.15
    ÅĦst
    -0.15
    otts
    -0.15
    estroy
    -0.14
    onitor
    -0.13
    POSITIVE LOGITS
     resident
    0.34
     Resident
    0.30
     residents
    0.29
     Residents
    0.27
     withholding
    0.26
    resident
    0.26
     treaty
    0.25
    Residents
    0.24
     residency
    0.23
     Treaty
    0.22
    Activations Density 0.004%

    No Known Activations