INDEX

Explanations

occurrences of specific names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ardon

-0.17

Ð°Ð½Ð¾

-0.15

èĨľ

-0.14

ÑĨÐµÐ·

-0.14

loe

-0.14

 Arbitrary

-0.13

 Mare

-0.13

edor

-0.13

 Marino

-0.13

 Slot

-0.13

POSITIVE LOGITS

teil

0.16

eldorf

0.15

iej

0.15

 GOODMAN

0.15

MainFrame

0.15

strup

0.14

Jed

0.14

.hm

0.14

Santa

0.14

unya

0.14

Activations Density 0.374%

occurrences of specific names and titles

No Comments

No Known Activations