INDEX

Explanations

references to intelligence and cleverness

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ToBounds

-0.15

wards

-0.15

apia

-0.15

rones

-0.14

andum

-0.14

ignKey

-0.14

entes

-0.14

endale

-0.14

phans

-0.14

tega

-0.14

POSITIVE LOGITS

èģ

0.18

 Pearce

0.17

complex

0.14

ifter

0.14

.hm

0.14

ivi

0.14

con

0.14

Smarty

0.14

 complex

0.14

 ende

0.14

Activations Density 0.026%

references to intelligence and cleverness

No Comments

No Known Activations