INDEX

Explanations

code-related terms related to data reading and processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

std

-0.20

,std

-0.18

std

-0.18

(std

-0.18

 Standard

-0.16

 standard

-0.16

boost

-0.15

.Standard

-0.15

Standard

-0.15

 standards

-0.14

POSITIVE LOGITS

0.23

ptr

0.22

 NULL

0.22

_softc

0.22

(struct

0.22

hdr

0.22

->

0.22

,NULL

0.21

 struct

0.21

 pointer

0.21

Activations Density 0.080%

code-related terms related to data reading and processing

No Comments

No Known Activations