INDEX

Explanations

references to communication systems and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

indr

-0.15

olik

-0.15

ldb

-0.15

ãĥĭãĥ¼

-0.14

ãĥªãĥ¼ãĤº

-0.14

Ã©f

-0.14

allery

-0.14

AGO

-0.14

ulkan

-0.14

fillType

-0.14

POSITIVE LOGITS

no

0.74

 artÄ±k

0.51

no

0.45

no

0.41

 anymore

0.39

 longer

0.38

.no

0.38

now

0.36

ãģªãģıãģª

0.34

 ceased

0.34

Activations Density 0.338%

references to communication systems and concepts

No Comments

No Known Activations