INDEX

Explanations

terms related to office settings and administrative roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 ActionTypes

-0.16

æºĢ

-0.15

hz

-0.15

odos

-0.15

mts

-0.15

aldo

-0.15

mailto

-0.15

Ã¢r

-0.14

iques

-0.14

æ±¡

-0.14

POSITIVE LOGITS

 Chap

0.16

elin

0.16

 simp

0.15

 umbrella

0.15

asad

0.15

 chap

0.15

adow

0.14

immer

0.14

oplay

0.14

vida

0.14

Activations Density 0.008%

terms related to office settings and administrative roles

No Comments

No Known Activations