INDEX

Explanations

code-related elements and function calls in 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

aday

-0.15

/Index

-0.14

Ð²Ð¾Ð»

-0.14

Äįe

-0.14

zing

-0.14

ÏĦÏī

-0.14

entine

-0.13

 animations

-0.13

eless

-0.13

á»ĩ

-0.13

POSITIVE LOGITS

cv

0.36

CV

0.33

cv

0.33

(cv

0.32

Cv

0.28

=cv

0.28

CV

0.28

.CV

0.27

cv

0.25

.cv

0.25

Activations Density 0.031%

code-related elements and function calls in a programming context

No Comments

No Known Activations