INDEX

Explanations

business-related terms in the context of utilities and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

-0.17

.scalablytyped

-0.15

ÑĤÐ¾ÑĤ

-0.14

ici

-0.14

_TAC

-0.14

codegen

-0.14

izzes

-0.13

POSITIVE LOGITS

asca

0.16

IVAL

0.16

renom

0.15

others

0.14

 Laurel

0.14

reno

0.14

 others

0.14

uba

0.14

piration

0.14

Ø®Ø´

0.14

Activations Density 0.037%

business-related terms in the context of utilities and products

No Comments

No Known Activations

business-related terms in the context of utilities and products

No Comments

No Known Activations