INDEX

Explanations

contractions and possessive forms in the document

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

woff

-0.16

ologne

-0.15

tur

-0.14

æīĭãģ«

-0.14

 Ð·Ð°Ð²

-0.14

oggler

-0.14

agen

-0.14

asl

-0.14

Ùĩ

-0.14

 subclass

-0.13

POSITIVE LOGITS

allocator

0.15

Ãºa

0.14

eÃ§

0.14

elas

0.14

iÅŁ

0.13

dio

0.13

ãĤĤãģĨ

0.13

riott

0.13

ileo

0.13

Activations Density 0.093%

contractions and possessive forms in the document

No Comments

No Known Activations