INDEX

Explanations

statements of assertion or claims in the text

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

esser

-0.17

ics

-0.15

INTR

-0.15

 Ø¨Ø§Ø¯

-0.15

mana

-0.14

é¡

-0.14

iter

-0.14

erti

-0.14

eo

-0.13

 blockIdx

-0.13

POSITIVE LOGITS

0.16

0.14

urd

0.14

andalone

0.14

baugh

0.14

ions

0.14

bolt

0.13

 Getty

0.13

 Sommer

0.13

Activations Density 0.015%

statements of assertion or claims in the text

No Comments

No Known Activations