INDEX

Explanations

punctuation and symbols indicating structure or emphasis in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

.metamodel

-0.14

ãĤ¤ãĤ¯

-0.14

ÙħØ§ÙĦ

-0.14

Ī¬

-0.14

ĶåĽŀ

-0.13

 Aure

-0.13

+A

-0.13

 bidi

-0.13

ÑĮÐµ

-0.13

Ĥ¹

-0.13

POSITIVE LOGITS

0.17

Fol

0.17

 yesterday

0.17

stery

0.16

 Yesterday

0.15

 IDirect

0.15

esterday

0.15

defaults

0.14

ollow

0.14

Yesterday

0.14

Activations Density 0.049%

punctuation and symbols indicating structure or emphasis in the text

No Comments

No Known Activations