INDEX

Explanations

words that indicate conditions or characteristics of a situation or entity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

clud

-0.20

aut

-0.16

apore

-0.15

agas

-0.15

ì°©

-0.14

anki

-0.14

less

-0.14

enor

-0.14

utor

-0.13

POSITIVE LOGITS

æ£

0.16

_od

0.15

 winning

0.15

éĹľ

0.15

Ã¤n

0.15

rep

0.15

\:

0.14

ATIVE

0.14

Ã©nom

0.13

;:

0.13

Activations Density 0.001%

words that indicate conditions or characteristics of a situation or entity

No Comments

No Known Activations