INDEX

Explanations

phrases indicating uncertainty or lack of clarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

cken

-0.16

 excelente

-0.14

ucci

-0.14

 Ð¿ÑĢÐµÐºÑĢÐ°Ñģ

-0.14

 courte

-0.14

agas

-0.14

 bazen

-0.14

vier

-0.13

 tremend

-0.13

Nor

-0.13

POSITIVE LOGITS

 actually

0.40

 actual

0.38

 truly

0.33

actually

0.31

 explicitly

0.31

çľŁæŃ£

0.31

 directly

0.30

 really

0.29

 Actually

0.28

 wirklich

0.28

Activations Density 0.036%

phrases indicating uncertainty or lack of clarity

No Comments

No Known Activations