© 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. 30-LLAMASCOPE-RES-32K
    11. 4805
    Prev
    Next
    INDEX
    Explanations

    financial planning and budget-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stuff
    -0.24
    ths
    -0.21
    们
    -0.20
    nds
    -0.19
     portions
    -0.17
    appings
    -0.17
    abouts
    -0.17
    sts
    -0.17
    ties
    -0.16
     evidence
    -0.16
    POSITIVE LOGITS
     that
    0.22
     recommendation
    0.20
     worth
    0.19
     thats
    0.19
     opportunity
    0.18
    ful
    0.18
     whose
    0.18
     assignment
    0.17
     proposal
    0.17
     instance
    0.17
    Activations Density 1.691%

    No Known Activations