INDEX

Explanations

expressions of self-reflection or rhetorical questions directed at the reader

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

tingham

-0.15

 Ð·Ð°Ñħ

-0.15

jerne

-0.15

.sep

-0.14

Ã©n

-0.14

atings

-0.14

trys

-0.14

allas

-0.14

tal

-0.13

Sep

-0.13

POSITIVE LOGITS

MT

0.16

odzi

0.15

 defs

0.15

dex

0.15

aura

0.14

odic

0.14

eker

0.14

odal

0.13

 slick

0.13

IDEO

0.13

Activations Density 0.123%

expressions of self-reflection or rhetorical questions directed at the reader

No Comments

No Known Activations