INDEX

Explanations

complex mathematical expressions and scientific terminologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ð¾Ð»Ð¾Ð´

-0.13

anova

-0.13

ENCHMARK

-0.13

awks

-0.13

Ãºsqueda

-0.12

/original

-0.12

rowsable

-0.12

Ð¾ÑģÐ¾Ð±

-0.12

.MixedReality

-0.12

 opendir

-0.12

POSITIVE LOGITS

0.12

 (“

0.12

marsh

0.12

igslist

0.11

nel

0.11

 ìĿĺíķ´

0.11

 ticking

0.11

ointed

0.11

 Simpson

0.11

arnation

0.11

Activations Density 9.332%

complex mathematical expressions and scientific terminologies

No Comments

No Known Activations