INDEX

Explanations

numerical data related to estimates and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

aley

-0.16

().'/

-0.14

 báº¡c

-0.14

ä¹ħ

-0.14

enko

-0.14

 closest

-0.14

inic

-0.14

orman

-0.13

riad

-0.13

POSITIVE LOGITS

 third

0.82

third

0.74

 THIRD

0.68

Third

0.65

-third

0.65

 fifth

0.65

 Third

0.65

ç¬¬ä¸ī

0.63

 thirds

0.62

 fourth

0.58

Activations Density 0.108%

numerical data related to estimates and statistics

No Comments

No Known Activations