INDEX

Explanations

terms related to progress or improvement in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

è£Ŀ

-0.17

.opend

-0.17

 Hoch

-0.16

hack

-0.14

erland

-0.14

èĢ³

-0.14

cean

-0.14

aph

-0.14

_seqs

-0.14

atility

-0.13

POSITIVE LOGITS

0.14

gi

0.14

VOKE

0.14

imler

0.14

æľ

0.14

_layer

0.14

 Heidi

0.14

ghi

0.14

ubar

0.13

edition

0.13

Activations Density 0.004%

terms related to progress or improvement in various fields

No Comments

No Known Activations