INDEX

Explanations

references to specific people and notable events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Me

-0.17

Me

-0.17

labs

-0.16

ç«ł

-0.16

me

-0.16

NECT

-0.16

me

-0.16

_me

-0.15

antas

-0.15

 tinh

-0.15

POSITIVE LOGITS

-per

0.16

 Cort

0.15

orted

0.15

mav

0.15

reu

0.14

mus

0.14

apiro

0.14

oto

0.14

estar

0.14

per

0.13

Activations Density 0.039%

references to specific people and notable events

No Comments

No Known Activations