INDEX

Explanations

references to legal or governmental entities and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

-Sep

-0.17

illard

-0.16

taÅŁ

-0.15

INF

-0.15

Cop

-0.15

.tom

-0.15

_CRC

-0.15

PEAT

-0.14

ë¶

-0.14

 Coch

-0.14

POSITIVE LOGITS

istle

0.17

uids

0.16

owe

0.16

 æ¥

0.15

ÛĮØ³Øª

0.15

ieber

0.15

&action

0.15

cid

0.14

elson

0.14

 Mein

0.14

Activations Density 0.021%

references to legal or governmental entities and actions

No Comments

No Known Activations