INDEX

Explanations

mentions of urban locations, specifically cities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

kab

-0.16

_accessible

-0.14

ML

-0.14

 toll

-0.14

 Ø±ÙĪØ³ØªØ§

-0.14

Ã©is

-0.14

 homer

-0.13

ÏĩÎ±

-0.13

wer

-0.13

awan

-0.13

POSITIVE LOGITS

FRING

0.18

HandlerContext

0.15

zek

0.15

agua

0.15

Ø¯Ø§ÙĨ

0.15

gil

0.14

hiba

0.14

ÑĥÑģÐº

0.14

Ä±rak

0.14

.IContainer

0.14

Activations Density 0.004%

mentions of urban locations, specifically cities

No Known Activations