INDEX

Explanations

references to time frames and sequence of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

UBLE

-0.19

ucs

-0.17

ãģ°

-0.17

arcy

-0.16

alia

-0.15

bd

-0.15

eparator

-0.14

verse

-0.14

zcze

-0.14

ogy

-0.14

POSITIVE LOGITS

oks

0.17

ega

0.15

tex

0.14

 ideal

0.14

onda

0.14

IFEST

0.14

.typ

0.13

ÑĩÐµÑģÐºÐ¸

0.13

ØŃÙĬ

0.13

Activations Density 0.052%

references to time frames and sequence of events

No Comments

No Known Activations

references to time frames and sequence of events

No Comments

No Known Activations