INDEX

Explanations

expressions related to measurement and specifications

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

enso

-0.16

acket

-0.15

orate

-0.14

ë²Į

-0.14

inia

-0.14

ãĤĩãģĨ

-0.14

apons

-0.14

outine

-0.14

motion

-0.13

limited

-0.13

POSITIVE LOGITS

anas

0.17

croft

0.17

 levels

0.16

arl

0.16

 assort

0.16

XHR

0.16

 level

0.15

_TB

0.15

lvl

0.15

levels

0.15

Activations Density 0.228%

expressions related to measurement and specifications

No Comments

No Known Activations