INDEX

Explanations

phrases that indicate a sense of inclusion or coverage in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

quential

-0.17

eeper

-0.16

 Svens

-0.14

.Align

-0.14

erable

-0.14

ÛĮØ§ÙĨ

-0.14

Ø§ÛĮØ´

-0.14

ozem

-0.14

evi

-0.14

UCT

-0.14

POSITIVE LOGITS

 range

0.17

 ÑģÐ¾Ð±Ð¾Ð¹

0.15

 duty

0.15

åģ¥

0.15

 ÑģÐ¾Ð±Ð¾Ñİ

0.14

èĮĥåĽ´

0.14

ch

0.14

ç¯Ħ

0.14

 dall

0.14

 RANGE

0.14

Activations Density 0.033%

phrases that indicate a sense of inclusion or coverage in a context

No Comments

No Known Activations