INDEX

Explanations

references to presidential candidates and elections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

imar

-0.18

.RightToLeft

-0.16

vÄĽ

-0.15

iesen

-0.15

å±ħ

-0.14

oot

-0.14

voor

-0.14

 Easter

-0.14

"display

-0.14

POSITIVE LOGITS

anza

0.15

ãĥ«ãĥī

0.15

 apart

0.14

anse

0.14

kont

0.14

enza

0.14

owler

0.14

fold

0.13

plr

0.13

æµģéĩı

0.13

Activations Density 0.005%

references to presidential candidates and elections

No Comments

No Known Activations