INDEX

Explanations

high-end products or services and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

inel

-0.16

stal

-0.15

ÃŃnÄĽ

-0.14

se

-0.14

Ãłn

-0.14

Å¥

-0.14

atre

-0.14

æĺĩ

-0.14

_bh

-0.13

ode

-0.13

POSITIVE LOGITS

utherford

0.15

 Mata

0.15

NAL

0.14

LICENSE

0.14

 Centro

0.13

ysz

0.13

efa

0.13

wig

0.13

imon

0.13

nable

0.13

Activations Density 0.012%

high-end products or services and their attributes

No Comments

No Known Activations