INDEX

Explanations

phrases indicating centrality or importance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

repid

-0.16

raki

-0.15

Ð¿ÑĢÐ°

-0.15

StateException

-0.15

orelease

-0.15

empre

-0.15

ERSIST

-0.15

eyse

-0.15

WSTR

-0.14

dik

-0.14

POSITIVE LOGITS

 Vick

0.14

ablish

0.14

asa

0.14

phinx

0.14

zÃ¡

0.13

allee

0.13

Od

0.13

 Sans

0.13

 upset

0.13

ancybox

0.13

Activations Density 0.012%

phrases indicating centrality or importance in various contexts

No Comments

No Known Activations