INDEX

Explanations

references to quantity or significant numerical values related to topics discussed

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

istrovstvÃŃ

-0.16

egan

-0.16

iple

-0.15

oris

-0.15

alon

-0.15

æħ

-0.14

 Chun

-0.14

rotch

-0.14

efully

-0.13

uple

-0.13

POSITIVE LOGITS

elu

0.17

 Compact

0.14

lesen

0.14

uja

0.14

 Lone

0.14

til

0.13

 fram

0.13

Įĵ

0.13

urar

0.13

 sudden

0.13

Activations Density 0.000%

references to quantity or significant numerical values related to topics discussed

No Comments

No Known Activations