INDEX

Explanations

numerical data and statistics related to entities and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

dim

-0.14

att

-0.14

uries

-0.14

dr

-0.14

heel

-0.14

ocl

-0.14

retch

-0.14

eding

-0.13

adel

-0.13

zon

-0.13

POSITIVE LOGITS

èħ¾

0.15

'gc

0.14

Kar

0.13

 Hess

0.13

rÃ¡n

0.13

ARB

0.13

egl

0.13

 Circle

0.13

eka

0.13

emouth

0.13

Activations Density 0.070%

numerical data and statistics related to entities and events

No Comments

No Known Activations