INDEX

Explanations

references to family and children

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

YTE

-0.16

oz

-0.15

isd

-0.15

Resolver

-0.14

 youth

-0.14

AdapterFactory

-0.14

ivism

-0.14

Ð»ÐºÐ¸

-0.14

 Vital

-0.14

orno

-0.14

POSITIVE LOGITS

Gim

0.16

 Chan

0.15

odic

0.14

etsk

0.13

'gc

0.13

quia

0.13

undi

0.13

ematik

0.13

 streak

0.13

Activations Density 0.045%

references to family and children

No Comments

No Known Activations