INDEX

Explanations

phrases indicating uncertainty or the current state of affairs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

zin

-0.16

 pron

-0.15

erate

-0.13

clist

-0.13

 lagi

-0.13

 ÑģÐ¾Ñģ

-0.13

als

-0.13

æĺŃ

-0.13

deny

-0.13

ntity

-0.13

POSITIVE LOGITS

etimes

0.16

aways

0.16

aped

0.16

olare

0.15

-mÃªme

0.15

jak

0.14

Schedulers

0.14

aday

0.14

igu

0.14

apa

0.14

Activations Density 0.241%

phrases indicating uncertainty or the current state of affairs

No Comments

No Known Activations