© 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. 28-LLAMASCOPE-RES-32K
    11. 30930
    Prev
    Next
    INDEX
    Explanations

    connections between individual actions and their broader societal implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unately
    -0.18
    alles
    -0.15
    Ïĥαν
    -0.15
    ghest
    -0.15
    lients
    -0.14
    olutely
    -0.14
    oda
    -0.14
    ignite
    -0.13
    isu
    -0.13
    adians
    -0.13
    POSITIVE LOGITS
     thereby
    0.31
     automatically
    0.25
     effectively
    0.24
     risk
    0.23
     Risk
    0.23
     essentially
    0.23
     risks
    0.22
    risk
    0.22
     instantly
    0.21
     automatic
    0.21
    Activations Density 0.316%

    No Known Activations