INDEX

Explanations

expressions related to consumer behavior and investment decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

sell

-0.15

ape

-0.15

egen

-0.15

opic

-0.14

bens

-0.14

asar

-0.14

landers

-0.13

itle

-0.13

acer

-0.13

çĩ

-0.13

POSITIVE LOGITS

 purchase

0.20

okane

0.17

 purchases

0.17

essler

0.16

pr

0.16

purchase

0.16

 expense

0.16

 Purchase

0.16

 justified

0.16

Purchase

0.16

Activations Density 0.299%

expressions related to consumer behavior and investment decisions

No Comments

No Known Activations