© 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. 233
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their actions or statements

    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
     Conserv
    -0.32
     conservatism
    -0.31
     conservatives
    -0.30
     Conservatives
    -0.30
     conserv
    -0.27
     Conservative
    -0.27
     GOP
    -0.25
     conservative
    -0.24
    GOP
    -0.24
    Republican
    -0.23
    POSITIVE LOGITS
     Democratic
    0.48
     Dem
    0.45
     DEM
    0.44
     progressive
    0.43
     Democr
    0.42
    Dem
    0.41
    æ°ij主
    0.40
    DEM
    0.39
    Democratic
    0.39
     Democrats
    0.38
    Activations Density 0.206%

    No Known Activations