INDEX

Explanations

mentions of locations and their associated political or social context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

eut

-0.16

Attachments

-0.15

éĢļ

-0.15

ele

-0.14

qd

-0.14

andler

-0.14

earing

-0.14

 Parsons

-0.14

ove

-0.14

Ãºt

-0.14

POSITIVE LOGITS

ctp

0.17

awei

0.16

otte

0.15

actable

0.15

omics

0.15

thr

0.14

orsi

0.14

Ã¶g

0.14

rem

0.14

TECT

0.14

Activations Density 0.252%

mentions of locations and their associated political or social context

No Comments

No Known Activations