INDEX

Explanations

phrases indicating completion or resolution of experiences

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

elow

-0.16

******↵↵

-0.14

ossier

-0.14

atra

-0.14

 scal

-0.14

izzo

-0.14

(Op

-0.14

èĬ¸

-0.14

xea

-0.14

ÑĢÐ¸Ð²Ð°

-0.13

POSITIVE LOGITS

 over

0.69

 Over

0.50

Over

0.49

over

0.48

_over

0.47

 OVER

0.47

-over

0.43

 sobre

0.42

.over

0.41

è¿ĩ

0.40

Activations Density 0.089%

phrases indicating completion or resolution of experiences

No Comments

No Known Activations