INDEX

Explanations

references to specific locations and their rankings or designations

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

ÐµÐ»ÐµÑĦ

-0.17

UNS

-0.15

fik

-0.14

sov

-0.14

ãĤ¤ãĤº

-0.14

UA

-0.14

ØªØ³

-0.14

ela

-0.13

POSITIVE LOGITS

_probe

0.14

ÃŃna

0.14

/MPL

0.14

 Kron

0.14

.Fat

0.14

 Fior

0.14

aginator

0.13

å

0.13

ajs

0.13

KIT

0.13

Activations Density 0.028%

references to specific locations and their rankings or designations

No Comments

No Known Activations