INDEX

Explanations

numeric ranges and financial figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ëŀĢ

-0.17

 Overs

-0.15

EMS

-0.15

anst

-0.15

ç¾

-0.14

opi

-0.14

 Boss

-0.14

ilian

-0.14

efa

-0.14

 threshold

-0.14

POSITIVE LOGITS

 depending

0.15

iano

0.15

 Russell

0.14

Ķ

0.14

.Arg

0.14

ÐµÐ½ÑĤÐ°

0.14

ales

0.14

 travers

0.13

 ãĥķãĤ¡

0.13

entieth

0.13

Activations Density 0.039%

numeric ranges and financial figures

No Comments

No Known Activations