INDEX

Explanations

programming-related syntax and structures, particularly in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

/wp

-0.15

Äĥr

-0.14

arat

-0.14

^^^^

-0.14

enburg

-0.14

æĿ¡

-0.14

ighting

-0.13

rouw

-0.13

UCE

-0.13

rat

-0.13

POSITIVE LOGITS

ÏĢÎ¬

0.16

 Berk

0.15

áº¡o

0.14

 Dodd

0.14

-UA

0.14

ãĥĶãĥ¼

0.13

osate

0.13

.!

0.13

 GrÃ¼

0.13

iff

0.13

Activations Density 0.395%

programming-related syntax and structures, particularly in code

No Comments

No Known Activations