INDEX

Explanations

text indicating revisions or updates to articles and reports

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

erialize

-0.16

 Chew

-0.15

ulings

-0.15

deaux

-0.15

udeau

-0.15

iete

-0.14

ÏİÏģÎ±

-0.14

idden

-0.14

ritch

-0.14

println

-0.14

POSITIVE LOGITS

pen

0.15

pen

0.15

opot

0.14

Ð¸ÑĤÐ¾Ð²

0.13

hti

0.13

/original

0.13

Cpp

0.13

ster

0.13

isspace

0.13

forge

0.13

Activations Density 0.238%

text indicating revisions or updates to articles and reports

No Comments

No Known Activations