INDEX

Explanations

citation or reference formatting elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ounder

-0.14

isphere

-0.14

Ãºa

-0.14

ept

-0.14

ULA

-0.14

ÅĻich

-0.13

AQ

-0.13

Ã©ro

-0.13

ylvania

-0.13

EO

-0.13

POSITIVE LOGITS

0.16

etal

0.15

-widgets

0.14

'gc

0.14

urent

0.14

tvb

0.14

egin

0.14

 Scar

0.13

ebek

0.13

Activations Density 0.014%

citation or reference formatting elements

No Comments

No Known Activations