INDEX

Explanations

academic journal titles and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ox

-0.15

UED

-0.15

ota

-0.15

sg

-0.14

eter

-0.14

æģĴ

-0.14

aland

-0.14

 sticky

-0.14

 Halk

-0.14

ado

-0.14

POSITIVE LOGITS

usz

0.15

é³´

0.15

onda

0.15

ObjectContext

0.15

Vien

0.14

keterangan

0.14

ÅĤu

0.14

YSIS

0.14

TestFixture

0.13

Activations Density 0.072%

academic journal titles and references

No Comments

No Known Activations