© 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. 24-LLAMASCOPE-RES-32K
    11. 15604
    Prev
    Next
    INDEX
    Explanations

    keywords related to social and political issues, particularly surrounding support systems and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ°ij主
    -0.22
     liberal
    -0.21
     Democrat
    -0.21
     democr
    -0.21
     democratic
    -0.20
     liberals
    -0.20
     liberalism
    -0.20
     progressives
    -0.20
     democrat
    -0.20
     progressive
    -0.20
    POSITIVE LOGITS
     right
    0.35
     Conserv
    0.35
     conservative
    0.34
    åı³
    0.34
     Right
    0.33
     Tea
    0.32
     conservatives
    0.31
    Right
    0.31
     conserv
    0.31
    right
    0.30
    Activations Density 0.534%

    No Known Activations