INDEX

Explanations

keywords related to organizations and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

-0.15

èĲ

-0.15

Ð°Ð¹Ð´

-0.14

 Hindered

-0.14

occ

-0.13

 Champ

-0.13

para

-0.13

PÅĻi

-0.13

 GetUser

-0.13

bon

-0.13

POSITIVE LOGITS

.lucene

0.15

ller

0.15

PRETTY

0.14

tru

0.14

ÌĪ

0.14

.Emit

0.13

shed

0.13

ÑıÑĤÑĮ

0.13

aval

0.13

Ĭ

0.13

Activations Density 0.677%

keywords related to organizations and events

No Comments

No Known Activations