INDEX

Explanations

key terms related to consumer experiences and institutional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-0.16

itude

-0.14

 Pare

-0.14

çĴ

-0.14

oretical

-0.14

ê°Ĳ

-0.14

-0.13

ooter

-0.13

POSITIVE LOGITS

ucht

0.17

 overall

0.17

å¡ļ

0.16

ente

0.15

olson

0.15

entes

0.15

Ø§ÙĬØª

0.15

.initialize

0.15

hev

0.14

eldo

0.14

Activations Density 0.002%

key terms related to consumer experiences and institutional contexts

No Comments

No Known Activations