INDEX

Explanations

phrases indicating the outcome or consequence of actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

zos

-0.16

defs

-0.16

 Flake

-0.16

actionDate

-0.15

aterno

-0.15

PointerException

-0.15

hek

-0.14

-fw

-0.14

à¸Ħà¸§

-0.14

agog

-0.14

POSITIVE LOGITS

we

0.24

 tenemos

0.23

 have

0.19

_HAVE

0.18

we

0.18

have

0.17

å¾ĹåĪ°

0.17

æľī

0.17

.we

0.16

æĪĳä»¬

0.16

Activations Density 0.154%

phrases indicating the outcome or consequence of actions

No Comments

No Known Activations