© 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. 9247
    Prev
    Next
    INDEX
    Explanations

    sentences related to personal experiences and emotional connections

    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
     yourself
    -0.20
     à¤īसन
    -0.20
     itself
    -0.16
     Ø®ÙĪدش
    -0.15
     yours
    -0.15
    imler
    -0.15
     nó
    -0.15
     ours
    -0.14
     ê·¸ëĬĶ
    -0.13
    isiyle
    -0.13
    POSITIVE LOGITS
     their
    1.34
    their
    1.20
    Their
    1.16
     Their
    1.15
     иÑħ
    0.99
     THEIR
    0.98
     leurs
    0.94
     themselves
    0.94
     jejich
    0.93
     loro
    0.92
    Activations Density 4.097%

    No Known Activations