INDEX

Explanations

structured programming elements and syntax 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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

agner

-0.16

é¼ĵ

-0.16

Ã³wn

-0.14

oku

-0.14

-generator

-0.14

 haus

-0.14

æĸ½

-0.14

Ã¤ll

-0.14

otor

-0.13

lect

-0.13

POSITIVE LOGITS

 alphabet

0.15

graphics

0.15

ÙĬØ«

0.14

ÅĪ

0.14

 recip

0.14

 Bath

0.14

fraction

0.14

rej

0.13

ZN

0.13

Pam

0.13

Activations Density 0.068%

structured programming elements and syntax in code

No Comments

No Known Activations