INDEX

Explanations

phrases related to forward-looking statements and regulatory caveats

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

iele

-0.16

avery

-0.16

iggs

-0.15

 respectively

-0.15

-0.14

InSection

-0.14

-lite

-0.13

aticon

-0.13

aceous

-0.13

finity

-0.13

POSITIVE LOGITS

gon

0.15

er

0.15

 Bale

0.13

etch

0.13

urr

0.13

oss

0.12

etr

0.12

à¤¹à¤®

0.12

imus

0.12

_rw

0.12

Activations Density 0.209%

phrases related to forward-looking statements and regulatory caveats

No Comments

No Known Activations

phrases related to forward-looking statements and regulatory caveats

No Comments

No Known Activations