INDEX

Explanations

occurrences of function definitions and calls in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

iph

-0.16

igner

-0.15

éĤ

-0.15

ãģ¹

-0.14

acho

-0.14

ÑıÐ´

-0.14

anco

-0.14

gmt

-0.13

alc

-0.13

aqu

-0.13

POSITIVE LOGITS

Ð¾Ð±Ð°

0.16

ëĭĿ

0.16

 EXEMPLARY

0.16

zilla

0.16

fÃ¼

0.16

imoto

0.15

ÅĻez

0.15

istrovstvÃŃ

0.14

RIX

0.14

PCODE

0.14

Activations Density 0.096%

occurrences of function definitions and calls in programming code

No Comments

No Known Activations