INDEX

Explanations

connections and associations with alumni

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

ninger

-0.16

_mgr

-0.14

.scalablytyped

-0.14

NOI

-0.14

follower

-0.14

ounty

-0.14

igion

-0.14

Mig

-0.14

itic

-0.14

otta

-0.14

POSITIVE LOGITS

0.18

eyen

0.17

0.15

íĸ¥

0.15

Ire

0.14

 sheep

0.14

aÄį

0.14

0.13

Activations Density 0.081%

connections and associations with alumni

No Comments

No Known Activations