INDEX

Explanations

variations of the word "il" (e.g., "il," "cil") in reference to aspects of language or structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

er

-0.28

-0.24

Ùī

-0.23

esis

-0.21

-0.19

erer

-0.18

ellen

-0.18

esc

-0.18

elle

-0.18

Ð¸ÑģÑĤ

-0.18

POSITIVE LOGITS

waukee

0.24

osoph

0.23

houette

0.23

antro

0.21

lement

0.21

adelphia

0.20

osopher

0.20

icious

0.20

lico

0.20

ox

0.18

Activations Density 0.071%

variations of the word "il" (e.g., "il," "cil") in reference to aspects of language or structure

No Comments

No Known Activations