INDEX

Explanations

mathematical notations and symbols used in equations

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

bourg

-0.17

ekk

-0.16

ecess

-0.15

ledon

-0.15

odal

-0.14

edException

-0.14

itar

-0.14

cess

-0.14

PRINTF

-0.14

 velit

-0.14

POSITIVE LOGITS

quest

0.14

efa

0.14

xDA

0.14

hte

0.14

.opengl

0.13

ãĤĤãģĨ

0.13

Sav

0.13

vm

0.13

_Impl

0.13

])[

0.13

Activations Density 0.194%

mathematical notations and symbols used in equations

No Comments

No Known Activations