INDEX

Explanations

mathematical terms related to linear equations and operators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

yon

-0.15

 Thur

-0.15

kart

-0.14

åĴ²

-0.14

ichni

-0.14

subst

-0.14

 slip

-0.14

 param

-0.14

ites

-0.14

POSITIVE LOGITS

 columns

0.18

(:,

0.18

 íĸī

0.18

 column

0.17

VEC

0.17

ivec

0.17

-column

0.16

.Column

0.16

Vec

0.16

/column

0.16

Activations Density 0.027%

mathematical terms related to linear equations and operators

No Comments

No Known Activations