INDEX

Explanations

instances of subjective opinions and interpretations related to knowledge and understanding

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oi

-0.15

 Ø£Ø¬ÙĦ

-0.14

 instead

-0.13

ulia

-0.13

èªį

-0.13

xies

-0.13

è¯ĳ

-0.13

Äĵ

-0.13

NCY

-0.13

ledi

-0.12

POSITIVE LOGITS

 looking

0.47

 based

0.40

looking

0.39

 reading

0.39

 Based

0.35

Looking

0.33

 Looking

0.33

Based

0.33

based

0.32

reading

0.32

Activations Density 0.330%

instances of subjective opinions and interpretations related to knowledge and understanding

No Comments

No Known Activations