INDEX

Explanations

words related to government and its actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Å¡e

-0.18

iris

-0.17

 Stem

-0.15

Ã¢y

-0.15

 Leonard

-0.15

ugi

-0.14

 Beats

-0.14

 stem

-0.14

æķı

-0.14

lin

-0.14

POSITIVE LOGITS

Bol

0.17

enge

0.16

 Bair

0.16

ither

0.15

allback

0.14

rone

0.14

enso

0.14

ATALOG

0.14

fait

0.14

alm

0.14

Activations Density 0.012%

words related to government and its actions

No Comments

No Known Activations