INDEX

Explanations

references to varying levels and comparisons of heights or qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

/Page

-0.16

æĸ¯çī¹

-0.15

PGA

-0.15

:@"%@

-0.14

ovna

-0.14

owler

-0.14

Î³Î¿Ïħ

-0.13

pak

-0.13

ordova

-0.13

çĽĽ

-0.13

POSITIVE LOGITS

 point

1.11

 points

1.00

 Point

0.94

point

0.91

-point

0.90

 POINT

0.86

Point

0.84

 Points

0.84

points

0.83

çĤ¹

0.83

Activations Density 0.191%

references to varying levels and comparisons of heights or qualities

No Comments

No Known Activations