INDEX

Explanations

references to significant historical events or entities related to a specific region

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

áº»

-0.13

.ColumnHeader

-0.13

 DbSet

-0.13

]={↵

-0.12

ÏĨÎ·

-0.12

 Ngá»įc

-0.11

ernote

-0.11

Ð¸ÑĤÑĭ

-0.11

Ð¾ÑģÑĤÐµÐ¹

-0.11

ÑĮÐµ

-0.11

POSITIVE LOGITS

Ind

1.17

Ind

1.11

ind

1.09

ind

1.03

IND

1.02

IND

1.02

-ind

1.02

_ind

0.96

.ind

0.91

 Indy

0.90

Activations Density 0.474%

references to significant historical events or entities related to a specific region

No Comments

No Known Activations