INDEX

Explanations

punctuations and symbols indicating strong emotions or attention in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Å¥

-0.16

-0.15

MAND

-0.14

èĬĤ

-0.14

andin

-0.13

ï½

-0.13

ReadOnly

-0.13

nou

-0.13

ease

-0.13

_ops

-0.13

POSITIVE LOGITS

SizeMode

0.16

.scalablytyped

0.16

uten

0.15

(æľ¨

0.15

 Ð¾Ð³ÑĢÐ°

0.15

Ø³ÙĪ

0.15

uell

0.14

uby

0.14

presso

0.14

ttp

0.14

Activations Density 0.274%

punctuations and symbols indicating strong emotions or attention in the text

No Comments

No Known Activations