INDEX

Explanations

proper nouns, particularly names of authors and researchers in academic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

readcr

-0.15

upe

-0.15

perimental

-0.14

Ã¼rnberg

-0.14

abbit

-0.14

.sax

-0.14

agus

-0.13

itoris

-0.13

raith

-0.13

StorageSync

-0.13

POSITIVE LOGITS

 Haram

0.15

/gtest

0.14

Ø³ÙĪØ¨

0.13

ved

0.12

ACING

0.12

 rast

0.12

 pornografia

0.12

 aider

0.12

 preca

0.12

angers

0.12

Activations Density 0.144%

proper nouns, particularly names of authors and researchers in academic references

No Comments

No Known Activations