INDEX

Explanations

terms that convey positivity or appreciation

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

-0.17

ein

-0.15

afari

-0.14

.ll

-0.14

jud

-0.14

edb

-0.14

idy

-0.13

umin

-0.13

oric

-0.13

-License

-0.13

POSITIVE LOGITS

-grand

0.21

lest

0.17

.epam

0.16

mente

0.16

awks

0.15

-looking

0.15

0.14

-quality

0.14

 ÑĢÐµÑĨÐµÐ¿

0.14

ammer

0.14

Activations Density 0.041%

terms that convey positivity or appreciation

No Comments

No Known Activations