INDEX

Explanations

terms related to organizations, industries, and events

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ayd

-0.18

 fold

-0.15

imited

-0.15

utenberg

-0.15

åĩ

-0.14

ÃŃÅ¾

-0.14

agr

-0.14

uen

-0.14

ophy

-0.14

oldem

-0.14

POSITIVE LOGITS

ollo

0.15

zn

0.15

amber

0.15

PID

0.14

RG

0.14

ettle

0.14

ILT

0.14

Ens

0.14

ØªØ±ÛĮ

0.14

è·¡

0.14

Activations Density 0.384%

terms related to organizations, industries, and events

No Comments

No Known Activations