INDEX

Explanations

programming-related terminology and functions for handling return values and results 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Priv

-0.17

_bases

-0.16

ÙĪØ§Ø¡

-0.14

reuse

-0.14

NGTH

-0.14

Ã©ro

-0.14

Reuse

-0.14

mo

-0.14

sur

-0.14

ten

-0.14

POSITIVE LOGITS

asca

0.17

abox

0.17

æ

0.16

ì±Ħ

0.16

radu

0.15

eket

0.15

resi

0.15

=output

0.15

 ÐĵÐŀ

0.14

Activations Density 0.065%

programming-related terminology and functions for handling return values and results in code

No Comments

No Known Activations