INDEX

Explanations

dates and years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

IEW

-0.15

.timeScale

-0.15

ATAB

-0.14

jest

-0.14

wahl

-0.13

ãģłãģ£ãģ¦

-0.13

ÑĩÐ¸ÑģÐ»

-0.13

ìĬ¬

-0.13

ustr

-0.13

 intermediary

-0.13

POSITIVE LOGITS

ainen

0.14

[assembly

0.14

ello

0.13

hem

0.13

ownt

0.13

Ð»Ñĥ

0.13

ego

0.13

LU

0.13

 Screw

0.13

 Rouge

0.12

Activations Density 0.033%

dates and years

No Comments

No Known Activations