INDEX

Explanations

expressions of evaluation and opinions regarding responses and criteria 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 @ 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

vrier

-0.17

ece

-0.15

et

-0.14

ÙĪÙĨØ¯

-0.14

cka

-0.14

ours

-0.14

ÐµÐ»ÑĮÐ·Ñı

-0.14

onor

-0.14

edor

-0.14

oksen

-0.14

POSITIVE LOGITS

incy

0.15

lake

0.15

ãĤĦãģĻ

0.14

0.13

 Pickup

0.13

 Inhal

0.13

yes

0.13

lld

0.13

 Kurd

0.13

Activations Density 0.239%

expressions of evaluation and opinions regarding responses and criteria in various contexts

No Comments

No Known Activations