INDEX

Explanations

references to the name "Frost" and variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 pronounced

-0.16

 Brunswick

-0.15

erb

-0.15

erta

-0.14

cores

-0.14

.synthetic

-0.14

 frequent

-0.14

uis

-0.14

onda

-0.14

 Delta

-0.14

POSITIVE LOGITS

é¾Ħ

0.16

Å¯v

0.15

leigh

0.15

LOCKS

0.15

.onView

0.14

ivid

0.14

à¸ī

0.14

gard

0.14

 BitConverter

0.14

makt

0.14

Activations Density 0.002%

references to the name "Frost" and variations of it

No Comments

No Known Activations