INDEX

Explanations

quantities related to challenges and conditions affecting various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

orne

-0.15

OTES

-0.15

rlen

-0.15

izi

-0.15

ucch

-0.14

ADM

-0.14

aker

-0.14

iges

-0.13

rael

-0.13

eral

-0.13

POSITIVE LOGITS

odyn

0.15

DeV

0.15

 aspect

0.15

 centrally

0.14

icio

0.14

 Aspect

0.14

 Judy

0.14

Ø±Ø¯Ø¯

0.13

xr

0.13

quer

0.13

Activations Density 0.321%

quantities related to challenges and conditions affecting various contexts

No Comments

No Known Activations