INDEX

Explanations

references to wearing or clothing items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

vier

-0.18

sexual

-0.16

iano

-0.16

TEGER

-0.16

ware

-0.16

RootElement

-0.15

Ã¨le

-0.15

uren

-0.15

wit

-0.15

ippi

-0.15

POSITIVE LOGITS

oldem

0.19

Beg

0.15

fol

0.15

ì´Ī

0.14

Bug

0.14

AGE

0.14

UPPORTED

0.14

ington

0.14

obia

0.14

edList

0.13

Activations Density 0.032%

references to wearing or clothing items

No Comments

No Known Activations