INDEX

Explanations

names and notable figures in various contexts

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

apult

-0.19

ÏģÎº

-0.18

-0.15

ØªØ±Ùĥ

-0.15

anten

-0.14

 Musk

-0.14

Ø§Ø¶Ø±

-0.14

stp

-0.13

à¹ĭ

-0.13

-pagination

-0.13

POSITIVE LOGITS

mts

0.17

aca

0.17

Moy

0.15

amen

0.14

aised

0.14

HIT

0.14

à¸²à¸«

0.13

Earn

0.13

etest

0.13

ITIONS

0.13

Activations Density 0.016%

names and notable figures in various contexts

No Comments

No Known Activations