INDEX

Explanations

references to the word "the" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

boy

-0.16

anim

-0.16

Ã±

-0.15

Boy

-0.14

ÑĥÑĢÐ¸

-0.14

alborg

-0.13

Boy

-0.13

.tel

-0.13

 caffe

-0.13

priv

-0.13

POSITIVE LOGITS

iddy

0.18

ashed

0.17

Byl

0.15

âĶĺ

0.15

utsch

0.14

 hard

0.14

 medium

0.14

bus

0.14

 Rubin

0.14

âĶĲ

0.14

Activations Density 0.025%

references to the word "the" and its variations in context

No Comments

No Known Activations