INDEX

Explanations

assert statements used in testing code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

zig

-0.16

itted

-0.16

itters

-0.15

cms

-0.15

ugh

-0.15

erman

-0.15

loo

-0.15

 Santana

-0.14

akt

-0.14

éĽ·

-0.14

POSITIVE LOGITS

sÄ±z

0.16

edly

0.15

ãĥ£

0.14

imed

0.14

 Ãĸn

0.14

oucher

0.13

icht

0.13

ments

0.13

ursday

0.13

Activations Density 0.007%

assert statements used in testing code

No Comments

No Known Activations