INDEX

Explanations

references to the number "two."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Cypress

-0.16

ivate

-0.15

.ptr

-0.15

Sau

-0.14

adam

-0.14

Ã³mo

-0.14

erais

-0.14

yna

-0.14

 fÃ¸

-0.14

inton

-0.14

POSITIVE LOGITS

.intellij

0.19

atura

0.18

.lesson

0.16

vester

0.15

´

0.15

Ã¼rn

0.14

_VERBOSE

0.14

sca

0.14

------+------+

0.14

 controvers

0.13

Activations Density 0.020%

references to the number "two."

No Comments

No Known Activations