INDEX

Explanations

terms related to abbreviations and acronyms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ipse

-0.16

onas

-0.16

-0.15

otch

-0.15

enth

-0.15

onder

-0.15

ucher

-0.15

ouz

-0.15

lsi

-0.14

rale

-0.14

POSITIVE LOGITS

jÃŃm

0.18

0.14

owie

0.14

ÃŃnÄĽ

0.14

ï¼«

0.14

æĺŃ

0.14

Î®Î½

0.14

lÃ¡d

0.14

ç¼

0.13

resizing

0.13

Activations Density 0.099%

terms related to abbreviations and acronyms

No Comments

No Known Activations