INDEX

Explanations

numerical values associated with prices or costs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ennes

-0.16

oki

-0.15

inf

-0.15

-0.14

sex

-0.14

 Infrastructure

-0.14

eo

-0.14

 vend

-0.14

POSITIVE LOGITS

alnÄ±z

0.17

orget

0.16

Ø¹Ø§Ø±

0.16

chyb

0.15

 Rosenberg

0.15

xea

0.15

.mybatisplus

0.14

olia

0.14

ripsi

0.14

Å¾enÃŃ

0.14

Activations Density 0.059%

numerical values associated with prices or costs

No Comments

No Known Activations