INDEX

Explanations

strings related to digital or coding terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

agini

-0.17

unch

-0.15

 Gould

-0.15

ì£

-0.14

 tongues

-0.14

 karÄ±ÅŁ

-0.14

akat

-0.14

 æķħ

-0.14

ughty

-0.14

lst

-0.14

POSITIVE LOGITS

//:

0.23

dna

0.21

DNA

0.19

ta

0.18

ret

0.17

/sn

0.17

ti

0.17

tuo

0.17

ru

0.16

DNA

0.15

Activations Density 0.006%

strings related to digital or coding terminology

No Comments

No Known Activations