INDEX

Explanations

sections of code and debugging information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

InSeconds

-0.14

inston

-0.14

lus

-0.14

pii

-0.14

apur

-0.13

_SYS

-0.13

pio

-0.13

 author

-0.13

Maz

-0.13

POSITIVE LOGITS

ICODE

0.17

(mi

0.15

ALCHEMY

0.15

ÙĪØ¯Ùĩ

0.14

ãĥĥãĥĪ

0.14

icode

0.14

STRU

0.14

ìĤ¬ì§Ģ

0.14

 affili

0.14

Activations Density 0.026%

sections of code and debugging information

No Comments

No Known Activations