INDEX

Explanations

sequences of characters indicating numeric identifiers or legal citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

icha

-0.15

arket

-0.14

å»Ĭ

-0.14

 GenerationType

-0.14

unden

-0.14

precated

-0.14

ãģŁãĤĬ

-0.14

rive

-0.14

insula

-0.13

cid

-0.13

POSITIVE LOGITS

Abb

0.16

Pun

0.15

enes

0.15

ãĥ³ãĤº

0.15

 Norm

0.14

 Punk

0.14

uth

0.14

 Innoc

0.13

igh

0.13

*&

0.13

Activations Density 0.050%

sequences of characters indicating numeric identifiers or legal citations

No Comments

No Known Activations