INDEX

Explanations

tokens related to geographical locations and timestamps

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

wend

-0.16

allis

-0.15

aben

-0.15

utta

-0.14

arena

-0.14

erald

-0.14

ÑģÑĤÐ²Ð¾ÑĢ

-0.13

_CURSOR

-0.13

ino

-0.13

POSITIVE LOGITS

çĶ

0.14

 Hemp

0.14

 redes

0.14

ìĥµ

0.14

jour

0.14

drm

0.14

ĵ°

0.13

ÑĨÐµÑĢ

0.13

UGC

0.13

fax

0.13

Activations Density 0.055%

tokens related to geographical locations and timestamps

No Comments

No Known Activations