INDEX

Explanations

numeric values related to statistics and metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ear

-0.18

otti

-0.16

cheid

-0.15

chÃ©

-0.15

ander

-0.15

hed

-0.15

AILS

-0.15

unci

-0.15

Ear

-0.14

 lá»ĩ

-0.14

POSITIVE LOGITS

TextLabel

0.16

ivot

0.16

?action

0.15

oho

0.15

lexport

0.15

osg

0.15

.Executor

0.15

&action

0.15

elson

0.15

ixin

0.15

Activations Density 0.267%

numeric values related to statistics and metrics

No Comments

No Known Activations