INDEX

Explanations

technical terms related to data structures and programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

iya

-0.14

hus

-0.14

acob

-0.14

Mug

-0.14

idel

-0.13

hus

-0.13

Î´Î®

-0.13

umper

-0.13

grown

-0.13

 fort

-0.13

POSITIVE LOGITS

forall

0.20

 forall

0.19

 Bool

0.19

 Walters

0.16

->

0.16

IO

0.15

IO

0.15

 ->↵

0.15

 FilePath

0.15

Int

0.15

Activations Density 0.001%

technical terms related to data structures and programming concepts

No Comments

No Known Activations