INDEX

Explanations

code-related terms and structures within a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

iasi

-0.15

stops

-0.15

lags

-0.14

 Dere

-0.14

 Mand

-0.14

 fare

-0.14

RSS

-0.13

avic

-0.13

lag

-0.13

Bus

-0.13

POSITIVE LOGITS

opal

0.18

ETCH

0.17

etch

0.17

emy

0.16

Ø·ØŃ

0.16

ingham

0.15

 Klopp

0.14

Calibri

0.14

opard

0.14

akk

0.14

Activations Density 0.006%

code-related terms and structures within a programming context

No Comments

No Known Activations