INDEX

Explanations

discussions around socio-political and cultural criticism, particularly related to privilege and systemic issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ior

-0.17

oot

-0.15

ãĥ³ãĤ¹

-0.15

.jetbrains

-0.15

est

-0.14

WA

-0.14

emm

-0.14

WA

-0.13

Fol

-0.13

cho

-0.13

POSITIVE LOGITS

xCB

0.17

OMIC

0.16

ymes

0.15

 HÃ¼s

0.15

defer

0.15

deniz

0.15

Ð¾Ð´Ñĭ

0.15

ddy

0.15

elijk

0.14

//{{

0.14

Activations Density 0.006%

discussions around socio-political and cultural criticism, particularly related to privilege and systemic issues

No Comments

No Known Activations