INDEX

Explanations

quantitative data and trends in reports or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

retch

-0.16

ennai

-0.16

yms

-0.15

slideUp

-0.14

 kalp

-0.14

ìķķ

-0.14

erro

-0.14

 ÐĿÐ°Ñģ

-0.14

 viÃªn

-0.14

ookie

-0.14

POSITIVE LOGITS

reg

0.17

 spoiler

0.17

iban

0.15

 gradually

0.15

 repeatedly

0.14

reg

0.14

Pir

0.14

á»Ľ

0.14

develop

0.14

onder

0.14

Activations Density 0.223%

quantitative data and trends in reports or statements

No Comments

No Known Activations