INDEX

Explanations

individual profiles or descriptions of people, particularly focusing on their identity and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

insula

-0.16

mmc

-0.14

reau

-0.14

ê²¬

-0.14

ecast

-0.14

.consumer

-0.14

ired

-0.13

 firefighters

-0.13

etti

-0.13

EventArgs

-0.13

POSITIVE LOGITS

ess

0.16

ward

0.16

eyer

0.16

Ł

0.15

TP

0.15

elas

0.14

ESS

0.14

edo

0.14

ako

0.14

olars

0.13

Activations Density 0.020%

individual profiles or descriptions of people, particularly focusing on their identity and achievements

No Comments

No Known Activations