INDEX

Explanations

concepts related to theories and their applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

entifier

-0.18

Ã¡Äį

-0.17

ouch

-0.16

ÑĤÐ¾Ð¶

-0.15

mant

-0.15

ante

-0.15

tae

-0.15

usu

-0.14

 Assertion

-0.14

ree

-0.14

POSITIVE LOGITS

ERSHEY

0.17

 Thumb

0.16

oins

0.15

 underlying

0.15

ichel

0.14

ocache

0.14

 dÃµi

0.14

0.13

icken

0.13

ÙĨÚ¯

0.13

Activations Density 0.028%

concepts related to theories and their applications

No Comments

No Known Activations