INDEX

Explanations

keywords related to a specific entity or subject of importance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

roit

-0.15

gable

-0.14

arga

-0.14

Cv

-0.14

ongsTo

-0.13

swe

-0.13

ãĥ³ãĥ

-0.13

ustos

-0.13

LOPT

-0.13

elligence

-0.13

POSITIVE LOGITS

åĨĨ

0.16

 Ð¿ÑĸÐ´Ñģ

0.15

Touch

0.14

ãĥ¼ãĤ¿

0.14

ffect

0.14

ulin

0.14

Ã¶y

0.14

Ø§Ø·Ø¹Ø©

0.13

Ã¼nd

0.13

 defaultCenter

0.13

Activations Density 0.002%

keywords related to a specific entity or subject of importance

No Comments

No Known Activations