INDEX

Explanations

the use of the word "well" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 exactly

-0.16

rina

-0.15

-0.14

ast

-0.14

avia

-0.14

-0.13

yan

-0.13

ight

-0.13

POSITIVE LOGITS

tÃ¼

0.18

bos

0.16

interop

0.14

 THPT

0.14

izons

0.14

Interop

0.14

izzas

0.14

Ãºsqueda

0.14

ThanOr

0.14

tura

0.14

Activations Density 0.020%

the use of the word "well" in various contexts

No Comments

No Known Activations