INDEX

Explanations

occurrences of the word "ham" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

æ¾

-0.19

 ì¹¨

-0.15

lÃ¤

-0.15

Î³Ïĩ

-0.15

tÃŃ

-0.14

ÏĦÎ¿ÏħÏĤ

-0.14

Ĥæķ°

-0.14

 Ð²Ðº

-0.14

unger

-0.14

andon

-0.14

POSITIVE LOGITS

tere

0.15

 terminal

0.15

equ

0.15

 ende

0.14

_bind

0.14

neau

0.14

Ð¼Ðµ

0.13

arc

0.13

awning

0.13

Activations Density 0.006%

occurrences of the word "ham" and related terms

No Comments

No Known Activations