INDEX

Explanations

structured data elements within a technical or programming context

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

ison

-0.15

viso

-0.14

iska

-0.14

[=

-0.14

isons

-0.13

 Victor

-0.13

urname

-0.13

oland

-0.13

ambi

-0.13

amburg

-0.13

POSITIVE LOGITS

oir

0.18

braco

0.16

ignet

0.15

ÑĤÑĮÑģÑı

0.14

Î³ÎºÎ±

0.14

 âĸ³

0.14

heck

0.14

ogue

0.14

ipl

0.14

oci

0.14

Activations Density 0.004%

structured data elements within a technical or programming context

No Comments

No Known Activations