INDEX

Explanations

mentions of significant years, particularly those related to historical 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

serter

-0.18

ochen

-0.17

eds

-0.16

å¸¯

-0.16

adge

-0.14

ervlet

-0.14

cover

-0.14

adle

-0.14

ifen

-0.13

infeld

-0.13

POSITIVE LOGITS

OAD

0.16

Ð»Ð°Ð±

0.15

plib

0.15

fsp

0.14

Ùĩ

0.14

ALES

0.14

ÑĤÐµ

0.13

WS

0.13

OUR

0.13

Activations Density 0.006%

mentions of significant years, particularly those related to historical events

No Comments

No Known Activations