INDEX

Explanations

phrases emphasizing important observations or key points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

and

-0.16

ãģĿãģĵ

-0.16

 instead

-0.16

Å¾el

-0.15

ander

-0.15

-0.14

 elsewhere

-0.14

 only

-0.14

in

-0.14

POSITIVE LOGITS

 worth

0.23

 missing

0.18

 Worth

0.17

ÑĨÐµÐ½

0.17

worth

0.17

 besides

0.16

aside

0.16

agn

0.15

missing

0.15

_MISSING

0.15

Activations Density 0.170%

phrases emphasizing important observations or key points

No Comments

No Known Activations