INDEX

Explanations

programming-related queries and actions involving code manipulation and interactive elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 tend

-0.15

-0.14

ATAR

-0.14

pled

-0.14

meno

-0.13

ç«¯

-0.13

anch

-0.13

may

-0.13

POSITIVE LOGITS

afil

0.17

ersen

0.16

roe

0.16

taire

0.15

ullen

0.15

abra

0.15

æĹıèĩªæ²»

0.15

OMPI

0.15

alie

0.15

irit

0.15

Activations Density 0.071%

programming-related queries and actions involving code manipulation and interactive elements

No Comments

No Known Activations

programming-related queries and actions involving code manipulation and interactive elements

No Comments

No Known Activations