INDEX

Explanations

patterns in code, particularly the presence of function calls and their respective outputs or errors

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

 crown

-0.16

OLA

-0.16

th

-0.15

 trom

-0.14

 Crown

-0.14

dro

-0.14

ola

-0.14

uki

-0.14

ica

-0.14

ins

-0.13

POSITIVE LOGITS

oman

0.18

ë¡

0.18

eniable

0.16

ãİ¡

0.15

unning

0.14

ilos

0.14

iddleware

0.14

erah

0.14

GMEM

0.13

Activations Density 0.030%

patterns in code, particularly the presence of function calls and their respective outputs or errors

No Comments

No Known Activations