INDEX

Explanations

words that indicate the concept of "most" or high frequency in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

/Peak

-0.16

éĵº

-0.16

 Pope

-0.16

RuntimeObject

-0.15

 Poke

-0.14

 Pearce

-0.14

ÏĢÎ¹Ïĥ

-0.14

Pil

-0.14

alat

-0.13

Pipe

-0.13

POSITIVE LOGITS

 part

1.09

part

0.89

-part

0.84

 Part

0.83

Part

0.80

_part

0.78

 PART

0.77

 parts

0.74

 parte

0.72

.part

0.72

Activations Density 0.303%

words that indicate the concept of "most" or high frequency in various contexts

No Comments

No Known Activations