INDEX

Explanations

nouns and proper names, particularly in the context of events and achievements

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

Ì£

-0.17

macros

-0.17

bdb

-0.16

ours

-0.15

urette

-0.14

Ã§ek

-0.14

vak

-0.14

inho

-0.14

SWG

-0.14

Tho

-0.14

POSITIVE LOGITS

anut

0.16

æį·

0.15

ulen

0.15

iji

0.15

Äįet

0.14

wich

0.14

hr

0.14

Æ°a

0.13

Activations Density 0.067%

nouns and proper names, particularly in the context of events and achievements

No Comments

No Known Activations