INDEX

Explanations

specific features or specifications related to products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

cntl

-0.15

arden

-0.14

ieten

-0.14

INARY

-0.14

ê°ģ

-0.14

Roz

-0.14

POCH

-0.13

yat

-0.13

oen

-0.13

 ÙħØ¹Øª

-0.13

POSITIVE LOGITS

 Plus

0.80

 plus

0.79

Plus

0.71

plus

0.68

 PLUS

0.65

-plus

0.60

_plus

0.60

.plus

0.57

PLUS

0.56

_PLUS

0.49

Activations Density 0.099%

specific features or specifications related to products

No Comments

No Known Activations