INDEX

Explanations

references to personal career experiences and achievements

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

ï¼³

-0.16

ipline

-0.15

ÙĪÛĮØ´

-0.15

 yere

-0.14

urple

-0.14

lisi

-0.14

Ð°ÑĢÐ°Ð¼

-0.14

 Merrill

-0.14

nea

-0.13

senal

-0.13

POSITIVE LOGITS

uw

0.15

CJK

0.15

tah

0.14

 late

0.14

aby

0.14

asty

0.13

and

0.13

zahl

0.13

hangi

0.13

ibal

0.13

Activations Density 0.184%

references to personal career experiences and achievements

No Comments

No Known Activations