INDEX

Explanations

specific technical terms related to scientific and programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

cheid

-0.18

ict

-0.15

Bid

-0.15

.dev

-0.15

 Carry

-0.14

arih

-0.14

 ëı

-0.13

 Brennan

-0.13

anza

-0.13

weise

-0.13

POSITIVE LOGITS

ÑģÐ¾ÑĢ

0.16

rut

0.15

endi

0.15

.club

0.15

upertino

0.15

enty

0.14

.mit

0.14

inand

0.14

esser

0.14

mit

0.14

Activations Density 0.024%

specific technical terms related to scientific and programming contexts

No Comments

No Known Activations