INDEX

Explanations

references to modules or libraries in code snippets

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

fik

-0.16

sit

-0.15

thr

-0.14

coder

-0.14

 FindObjectOfType

-0.14

.MaxLength

-0.14

ifa

-0.14

Ð¾Ð¼ÐµÑĢ

-0.14

paRepository

-0.13

 Ting

-0.13

POSITIVE LOGITS

phalt

0.15

erras

0.15

 Watt

0.14

urt

0.14

urd

0.14

ynn

0.14

 sentiment

0.13

Î¼ÏīÎ½

0.13

ç´

0.13

ieten

0.13

Activations Density 0.002%

references to modules or libraries in code snippets

No Comments

No Known Activations