INDEX

Explanations

elements related to historical context and timeline events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ormsg

-0.16

mol

-0.16

adesh

-0.16

oningen

-0.15

adÃŃ

-0.15

Å¼

-0.15

reb

-0.15

eh

-0.15

jab

-0.15

ulta

-0.14

POSITIVE LOGITS

AGO

0.18

apan

0.17

som

0.14

amba

0.14

prise

0.14

endo

0.14

ãĤ¾

0.14

 Perc

0.14

INGTON

0.14

ington

0.13

Activations Density 0.418%

elements related to historical context and timeline events

No Comments

No Known Activations