INDEX

Explanations

instances of the word "don't" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

asca

-0.16

oons

-0.14

alink

-0.14

ervers

-0.14

ocks

-0.14

ãĥ¼ãĥ©

-0.14

ophon

-0.14

ÑĤÑĶ

-0.14

_IL

-0.14

noise

-0.14

POSITIVE LOGITS

0.15

ominator

0.15

Ø¹Ø¯

0.14

akin

0.14

YRO

0.13

TRS

0.13

heim

0.13

 lone

0.13

oxel

0.13

Activations Density 0.079%

instances of the word "don't" and its variations

No Comments

No Known Activations