INDEX

Explanations

phrases related to switching actions and transitions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Äįer

-0.15

ivant

-0.15

.sax

-0.15

MEA

-0.14

indre

-0.14

_PRIVATE

-0.14

Alive

-0.14

anz

-0.14

ayn

-0.14

Ont

-0.14

POSITIVE LOGITS

 pres

0.14

uye

0.14

BT

0.14

RefreshLayout

0.14

acket

0.14

Ã¤ch

0.14

0.13

 Trades

0.13

pic

0.13

Activations Density 0.047%

phrases related to switching actions and transitions

No Comments

No Known Activations