INDEX

Explanations

phrases related to contacting and requesting information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

°

-0.15

æı

-0.15

redo

-0.14

inka

-0.14

anta

-0.14

icipants

-0.13

fad

-0.13

hin

-0.13

aph

-0.13

lint

-0.13

POSITIVE LOGITS

 anything

0.17

anything

0.17

 bulk

0.17

 assistance

0.17

 further

0.16

 copies

0.16

 information

0.15

 specific

0.15

any

0.15

/request

0.15

Activations Density 0.145%

phrases related to contacting and requesting information

No Comments

No Known Activations