INDEX

Explanations

references to personal relationships and interactions

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

edition

-0.15

 Consort

-0.15

oust

-0.15

èµ·æĿ¥

-0.14

hem

-0.14

_Impl

-0.14

 ÑģÐµÐ±Ðµ

-0.14

imitives

-0.14

WS

-0.14

POSITIVE LOGITS

/us

0.19

/on

0.18

-mÃªme

0.18

Ø¯ÛĮÚ¯Ø±

0.17

oup

0.17

/her

0.16

 Ãºn

0.15

 Ð´Ð²Ð¾

0.15

datable

0.15

 Ð¡ÐµÑĢ

0.15

Activations Density 0.191%

references to personal relationships and interactions

No Comments

No Known Activations