INDEX

Explanations

quotations and dialogue in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ð°Ð»Ð¾Ð²

-0.15

_eof

-0.14

lose

-0.14

aty

-0.14

apo

-0.13

ised

-0.13

rawer

-0.13

ARI

-0.13

opian

-0.13

iset

-0.13

POSITIVE LOGITS

inda

0.17

eda

0.15

 robes

0.14

ICAST

0.14

hood

0.13

dbl

0.13

Å¾enÃŃ

0.13

 crack

0.13

mie

0.13

 Ð¼ÐµÐ¶

0.13

Activations Density 0.030%

quotations and dialogue in the text

No Comments

No Known Activations