INDEX

Explanations

specific tags and identifiers in the text, indicating notable content or important elements

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

ctal

-0.16

rent

-0.15

insky

-0.15

chaft

-0.15

otre

-0.15

shi

-0.15

ream

-0.14

 synthes

-0.14

íĦ°

-0.14

ucht

-0.14

POSITIVE LOGITS

hed

0.19

nat

0.15

 cardio

0.15

olet

0.15

 Horm

0.15

 hedge

0.14

.fb

0.14

 Ø±ÛĮ

0.14

iolet

0.14

Activations Density 0.002%

specific tags and identifiers in the text, indicating notable content or important elements

No Comments

No Known Activations