INDEX

Explanations

specific years and significant events related to history and notable dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ify

-0.15

idel

-0.15

ł

-0.15

iot

-0.14

nam

-0.14

OLF

-0.14

ius

-0.14

idelity

-0.14

POSITIVE LOGITS

okino

0.16

 Hlav

0.15

è»¢

0.15

ãĥªãĥ¼ãĤº

0.15

agina

0.15

$MESS

0.15

uml

0.15

ensively

0.14

æģ¯

0.14

áº£i

0.14

Activations Density 0.110%

specific years and significant events related to history and notable dates

No Comments

No Known Activations