INDEX

Explanations

conjunctions and phrases indicating a connection or addition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ÏģÎ¹Î¿

-0.15

ardo

-0.15

æ³

-0.15

ynos

-0.14

 overall

-0.14

atrix

-0.14

xon

-0.14

vester

-0.14

verts

-0.14

POSITIVE LOGITS

ATEST

0.15

raman

0.14

ensen

0.14

yses

0.14

lt

0.14

olt

0.14

angered

0.13

à¥Ĥà¤¤

0.13

ÑĩÐ¸Ð²

0.13

 amph

0.13

Activations Density 0.072%

conjunctions and phrases indicating a connection or addition

No Comments

No Known Activations