INDEX

Explanations

references to communication devices, particularly phones and calling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

eo

-0.15

onical

-0.14

claimer

-0.14

wn

-0.14

neg

-0.14

ìŀ¡ëĭ´

-0.14

iol

-0.13

 corners

-0.13

 Claims

-0.13

hart

-0.13

POSITIVE LOGITS

 BugÃ¼n

0.17

chef

0.16

razier

0.15

Decorator

0.14

gree

0.14

ighton

0.14

 Ø®ÙĦ

0.14

Decor

0.13

Ð¾Ð¼ÐµÑĤ

0.13

plotlib

0.13

Activations Density 0.195%

references to communication devices, particularly phones and calling

No Comments

No Known Activations