INDEX

Explanations

words related to organizational actions and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

er

-0.18

TURE

-0.16

tures

-0.16

ãģĦãĤĭ

-0.16

agher

-0.16

ieved

-0.15

iston

-0.15

clearfix

-0.15

ouses

-0.15

 pros

-0.14

POSITIVE LOGITS

ech

0.24

rop

0.22

reatment

0.21

rovers

0.20

issue

0.20

ream

0.20

roph

0.20

reated

0.20

olerance

0.19

opia

0.19

Activations Density 0.067%

words related to organizational actions and processes

No Comments

No Known Activations