INDEX

Explanations

sentences that use the word "like" to initiate comparisons or examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

åłĤ

-0.18

 EITHER

-0.16

 VerfÃ¼gung

-0.16

either

-0.16

illin

-0.14

onical

-0.14

.Îķ

-0.14

plemented

-0.14

orno

-0.14

ifix

-0.13

POSITIVE LOGITS

 many

0.41

 most

0.33

many

0.33

any

0.27

è®¸å¤ļ

0.26

Many

0.25

 MANY

0.25

 Many

0.24

 with

0.23

 everything

0.23

Activations Density 0.073%

sentences that use the word "like" to initiate comparisons or examples

No Comments

No Known Activations