INDEX

Explanations

terms associated with governance and representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

.setViewport

-0.17

atori

-0.16

anou

-0.15

rais

-0.15

ãģįãģª

-0.15

abaj

-0.15

atura

-0.14

ANNER

-0.14

ÙĲÙħ

-0.14

anner

-0.14

POSITIVE LOGITS

 Berm

0.16

.scalablytyped

0.16

oko

0.16

_mapped

0.15

resse

0.14

 ìĽĶ

0.14

iffies

0.14

ager

0.13

estar

0.13

@}

0.13

Activations Density 0.023%

terms associated with governance and representation

No Comments

No Known Activations