INDEX

Explanations

references to political events and figures in the context of elections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

osc

-0.17

Ð²Ð¾Ð»

-0.16

opping

-0.16

éĤ¦

-0.15

osta

-0.15

ogue

-0.15

 Sparks

-0.15

usta

-0.15

PDO

-0.14

.CreateIndex

-0.14

POSITIVE LOGITS

elan

0.16

erman

0.15

ÏĥÎ¼

0.15

Dream

0.15

ceph

0.14

unya

0.14

inou

0.14

iesz

0.14

 Dream

0.14

 Biden

0.14

Activations Density 0.244%

references to political events and figures in the context of elections

No Comments

No Known Activations