INDEX

Explanations

phrases related to notifications and warnings

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

mpar

-0.15

readcr

-0.15

Kir

-0.14

kili

-0.14

idar

-0.14

ARSE

-0.14

ario

-0.14

CLEAR

-0.14

wig

-0.14

(assert

-0.14

POSITIVE LOGITS

rev

0.18

ryption

0.16

APSHOT

0.15

ãĥ¯ãĥ¼

0.15

ycz

0.15

rev

0.15

ohan

0.14

Rev

0.14

ows

0.14

olle

0.14

Activations Density 0.004%

phrases related to notifications and warnings

No Comments

No Known Activations