INDEX

Explanations

military ranks and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

hlen

-0.17

Lem

-0.16

essen

-0.15

 Armen

-0.15

uyen

-0.15

leet

-0.14

ahu

-0.14

otten

-0.14

ogne

-0.14

edla

-0.14

POSITIVE LOGITS

 Welch

0.25

eshire

0.19

 Sher

0.18

 Terr

0.17

èħ

0.17

Rif

0.16

 Beds

0.16

sher

0.16

 Cold

0.16

 Buff

0.15

Activations Density 0.009%

military ranks and organizations

No Comments

No Known Activations