INDEX

Explanations

directional indicators related to geography or locations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

pery

-0.17

iez

-0.15

cac

-0.15

 Lange

-0.15

uder

-0.15

aeda

-0.15

ennon

-0.14

rid

-0.14

qua

-0.14

anny

-0.14

POSITIVE LOGITS

 ÙģØ§Ø±

0.15

.ElementAt

0.15

 Tick

0.15

ãĤĥ

0.14

æ³ķäºº

0.14

Ð»ÑĮÑĤ

0.13

oggles

0.13

.android

0.13

esters

0.13

ajan

0.13

Activations Density 0.013%

directional indicators related to geography or locations

No Comments

No Known Activations