INDEX

Explanations

references to individuals and their roles or titles within a formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

lis

-0.16

alis

-0.15

è£ı

-0.15

alach

-0.14

apan

-0.14

ExecutionContext

-0.14

omanip

-0.14

aldi

-0.14

é¼ł

-0.13

POSITIVE LOGITS

xon

0.15

 mixin

0.14

ï¼Īç¬ĳ

0.14

ãĤī

0.14

EDIA

0.14

etz

0.13

yms

0.13

dera

0.13

dia

0.13

enia

0.13

Activations Density 0.039%

references to individuals and their roles or titles within a formal context

No Comments

No Known Activations