INDEX

Explanations

phrases related to capabilities and rights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ãĥ¼ãĥ

-0.17

seau

-0.15

culate

-0.15

rag

-0.15

ULD

-0.14

erk

-0.14

adr

-0.14

ize

-0.14

rk

-0.14

Ø¬Ø¯

-0.13

POSITIVE LOGITS

0.19

æĲŃ

0.17

to

0.16

egasus

0.16

0.15

 Ches

0.14

cker

0.14

 íķĺì§Ģ

0.14

0.13

edy

0.13

Activations Density 0.084%

phrases related to capabilities and rights

No Comments

No Known Activations