INDEX

Explanations

phrases related to product features and benefits

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

çĻº

-0.16

amarin

-0.16

lest

-0.16

 Wheeler

-0.15

ughs

-0.14

Ø®Ùħ

-0.14

agnar

-0.14

ucas

-0.14

croft

-0.14

orman

-0.14

POSITIVE LOGITS

 fits

0.15

zel

0.15

ategor

0.14

 appeals

0.14

RET

0.14

 help

0.14

 Analy

0.14

Fit

0.13

StrictEqual

0.13

Activations Density 0.180%

phrases related to product features and benefits

No Comments

No Known Activations