INDEX

Explanations

automotive-related terminology and features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Ð¸Ð¼Ð¿

-0.14

.ov

-0.14

/Branch

-0.14

 adress

-0.13

éĽ

-0.13

oub

-0.13

gor

-0.13

bond

-0.13

agens

-0.13

POSITIVE LOGITS

ãĥ«ãĤ¯

0.15

ime

0.14

 Neal

0.13

Conversation

0.13

itmap

0.13

Ã¡ct

0.13

Ð¾ÑĤÐ°

0.13

 Morrison

0.13

coat

0.13

ava

0.13

Activations Density 0.008%

automotive-related terminology and features

No Comments

No Known Activations