INDEX

Explanations

negative forms and associated phrases regarding product expectations and performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

aggio

-0.19

bjerg

-0.16

iÃ³

-0.14

Spin

-0.14

ois

-0.14

CFG

-0.14

rst

-0.14

.Apis

-0.14

swire

-0.14

 Sparks

-0.14

POSITIVE LOGITS

olla

0.15

Pri

0.15

alf

0.14

Sul

0.14

ì¹

0.14

ãĥ³ãĥĹ

0.14

_alias

0.13

ya

0.13

 alias

0.13

Activations Density 0.000%

negative forms and associated phrases regarding product expectations and performance

No Comments

No Known Activations