INDEX

Explanations

mentions of domains and domain-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

quis

-0.16

erman

-0.16

ibr

-0.16

inks

-0.15

yr

-0.15

odos

-0.15

dy

-0.15

sk

-0.15

aker

-0.14

oma

-0.14

POSITIVE LOGITS

ONGL

0.16

-wide

0.15

CastException

0.15

estic

0.14

rak

0.14

åŁŁ

0.14

.Utc

0.14

 Hatch

0.14

Ngb

0.14

RunLoop

0.14

Activations Density 0.019%

mentions of domains and domain-related terminology

No Comments

No Known Activations