INDEX

Explanations

references to product usage and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

---</

-0.14

verting

-0.14

.matcher

-0.14

erner

-0.14

legg

-0.14

inks

-0.13

 Nate

-0.13

iegel

-0.13

/sys

-0.13

BorderStyle

-0.13

POSITIVE LOGITS

strup

0.18

uÄį

0.16

 Spinner

0.15

è´¨

0.14

 ofType

0.14

 newItem

0.14

Fitness

0.14

expo

0.14

 fitness

0.13

Activations Density 0.199%

references to product usage and evaluations

No Comments

No Known Activations