INDEX

Explanations

mentions of specific companies and industries, particularly in the energy and telecommunications sectors

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

GMEM

-0.16

rung

-0.14

onet

-0.14

.twimg

-0.14

oldt

-0.14

ffb

-0.14

 bench

-0.14

 menn

-0.14

=~

-0.14

 Bench

-0.14

POSITIVE LOGITS

anos

0.16

.yang

0.15

 Brick

0.15

apan

0.14

enta

0.14

oop

0.13

ano

0.13

unch

0.13

uur

0.13

Activations Density 0.061%

mentions of specific companies and industries, particularly in the energy and telecommunications sectors

No Comments

No Known Activations