INDEX

Explanations

geographical locations and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-0.15

emen

-0.15

ipp

-0.15

hle

-0.14

Yus

-0.14

leta

-0.14

elf

-0.14

ecs

-0.14

Maj

-0.14

echan

-0.14

POSITIVE LOGITS

çĶŁ

0.19

 born

0.18

 Born

0.16

Born

0.16

ONA

0.15

Ã¼stÃ¼

0.15

 raised

0.15

born

0.15

 grew

0.15

indo

0.15

Activations Density 0.057%

geographical locations and names

No Comments

No Known Activations