INDEX

Explanations

actions and movements signified by prepositions and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ekler

-0.15

ÐµÐ¶

-0.14

umbn

-0.14

ÐĬ

-0.14

<<<<<<<<

-0.13

CTIONS

-0.13

:@""

-0.13

kal

-0.13

IMARY

-0.13

erguson

-0.13

POSITIVE LOGITS

the

0.19

wards

0.19

/down

0.18

 some

0.18

0.17

0.15

/off

0.15

any

0.15

/up

0.14

lius

0.14

Activations Density 0.132%

actions and movements signified by prepositions and related terms

No Comments

No Known Activations