INDEX

Explanations

phrases indicating direction or purpose towards a goal or person

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

umba

-0.17

 ngang

-0.15

onu

-0.15

alue

-0.15

arel

-0.15

_MARKER

-0.14

avis

-0.13

gia

-0.13

-END

-0.13

illaume

-0.13

POSITIVE LOGITS

illac

0.16

0.15

à¹Ģà¸§à¸¥

0.15

uisine

0.15

ropp

0.15

 Throne

0.14

Slf

0.14

.sqlite

0.14

rop

0.13

efon

0.13

Activations Density 0.027%

phrases indicating direction or purpose towards a goal or person

No Comments

No Known Activations