INDEX

Explanations

phrases expressing gratitude or appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ezier

-0.17

_OM

-0.14

opsis

-0.14

arg

-0.14

.vendor

-0.13

boa

-0.13

 Cristiano

-0.13

ugh

-0.13

 star

-0.13

POSITIVE LOGITS

eker

0.17

ãĥ«ãĤ¯

0.17

ODY

0.16

ills

0.15

stru

0.15

Ä±rak

0.15

zyst

0.15

 intr

0.15

unker

0.14

edy

0.14

Activations Density 0.021%

phrases expressing gratitude or appreciation

No Comments

No Known Activations