INDEX

Explanations

formal mathematical expressions and descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

-0.16

omik

-0.15

oz

-0.15

 Nail

-0.15

arto

-0.14

yles

-0.14

rlen

-0.14

ÙģÙĪ

-0.14

eland

-0.14

reet

-0.14

POSITIVE LOGITS

culus

0.18

 Setter

0.15

 setter

0.15

idon

0.15

/Instruction

0.14

 setters

0.14

utenberg

0.14

gift

0.14

gress

0.13

attice

0.13

Activations Density 0.077%

formal mathematical expressions and descriptions

No Comments

No Known Activations