INDEX

Explanations

negations or phrases indicating exceptions and limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

.TypeOf

-0.15

ungan

-0.15

ÑĤÑĢÐ°

-0.14

 æĤ

-0.14

flt

-0.14

YW

-0.14

á»Ļi

-0.13

isko

-0.13

ERY

-0.13

 çĽ

-0.13

POSITIVE LOGITS

XCT

0.16

addock

0.15

ent

0.15

enton

0.14

ÐµÐ½ÑĤÑĥ

0.14

ycl

0.14

 leng

0.14

reon

0.14

0.13

Activations Density 0.083%

negations or phrases indicating exceptions and limitations

No Comments

No Known Activations