INDEX

Explanations

references to academic databases and scholarly resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

amil

-0.15

 Yard

-0.15

-modules

-0.14

_SLEEP

-0.14

olik

-0.14

ussy

-0.14

arked

-0.13

imb

-0.13

ades

-0.13

ars

-0.13

POSITIVE LOGITS

é¤¨

0.18

é¦Ĩ

0.15

Binding

0.15

ahir

0.15

heiro

0.14

ãĥ¼ãĥª

0.14

.Binding

0.14

 Cone

0.14

unger

0.14

rray

0.14

Activations Density 0.039%

references to academic databases and scholarly resources

No Comments

No Known Activations