INDEX

Explanations

instances of specific names, organizations, and their actions or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

gra

-0.19

-0.17

rem

-0.16

-0.15

Sha

-0.15

 refer

-0.15

oth

-0.15

ogen

-0.14

 Markets

-0.14

POSITIVE LOGITS

UsageId

0.16

ãĤ¤ãĥī

0.15

ocator

0.15

ysize

0.15

-mf

0.15

 Trails

0.15

esseract

0.15

GuidId

0.15

hear

0.15

INLINE

0.15

Activations Density 0.464%

instances of specific names, organizations, and their actions or attributes

No Comments

No Known Activations