INDEX

Explanations

references to historical structures and their uses over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

_SRV

-0.16

å£

-0.15

ap

-0.15

ÙĨØ¯Ø±

-0.14

Compiled

-0.14

.ServiceModel

-0.14

anh

-0.14

POSITIVE LOGITS

hiba

0.18

ovie

0.15

ov

0.15

ãĥĸãĥª

0.15

 æ©

0.14

ceae

0.14

Fee

0.14

Bom

0.14

uez

0.14

Ø°

0.14

Activations Density 0.453%

references to historical structures and their uses over time

No Comments

No Known Activations