INDEX

Explanations

elements of programming and information logging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

GMEM

-0.16

Å¯l

-0.15

/OR

-0.15

/*č↵

-0.15

inho

-0.15

ITERAL

-0.14

oller

-0.14

fragistics

-0.14

ROID

-0.14

sÄ±z

-0.14

POSITIVE LOGITS

0.22

 ãĢĬ

0.16

.NET

0.16

Ī

0.16

 LORD

0.15

CO

0.15

avel

0.14

eve

0.14

armor

0.14

Activations Density 0.169%

elements of programming and information logging

No Comments

No Known Activations