INDEX

Explanations

references to historical manuscripts and their details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 merch

-0.15

.documentation

-0.15

mares

-0.15

FX

-0.15

 æŃ

-0.15

 ØŃØ°

-0.14

olik

-0.14

_SERIAL

-0.14

Documentation

-0.14

Stride

-0.13

POSITIVE LOGITS

ms

0.26

MS

0.26

Cod

0.25

 manuscript

0.25

 parchment

0.24

cod

0.24

folios

0.24

cod

0.23

 illumination

0.23

 coder

0.23

Activations Density 0.073%

references to historical manuscripts and their details

No Comments

No Known Activations