INDEX

Explanations

mentions of diplomatic entities and their roles

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

adesh

-0.17

aring

-0.16

aldi

-0.15

atters

-0.15

Bug

-0.15

yat

-0.14

çİĩ

-0.14

Verdana

-0.14

beh

-0.14

ondo

-0.13

POSITIVE LOGITS

inch

0.16

ç®±

0.16

.Toolkit

0.15

 invis

0.15

LabelText

0.14

gett

0.14

mux

0.14

'&#

0.14

eneg

0.14

Wid

0.14

Activations Density 0.008%

mentions of diplomatic entities and their roles

No Comments

No Known Activations