INDEX

Explanations

proper nouns, particularly names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ropa

-0.15

APON

-0.14

pragma

-0.14

ague

-0.14

lopen

-0.13

ÏģÎº

-0.13

 Hastings

-0.13

ãĥ³ãĤ°

-0.13

olar

-0.13

res

-0.13

POSITIVE LOGITS

.Values

0.16

ucht

0.16

vla

0.15

otel

0.15

 HÃ¼s

0.15

bcd

0.14

Qualifier

0.14

 Ú©ÛĮÙĦ

0.14

 Bugs

0.14

iphery

0.14

Activations Density 0.001%

proper nouns, particularly names and titles

No Comments

No Known Activations