INDEX

Explanations

names of places and references to geographical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

antine

-0.15

 rumored

-0.15

 McMahon

-0.15

 rumor

-0.15

_refl

-0.15

AsyncResult

-0.15

 Ambient

-0.14

oppel

-0.14

 '../../../../../

-0.14

om

-0.13

POSITIVE LOGITS

AFP

0.27

AFP

0.25

/AFP

0.18

 jihadists

0.17

utos

0.17

 Observatory

0.16

\a

0.16

enas

0.16

ãĥŃãĥ³

0.16

asto

0.15

Activations Density 0.024%

names of places and references to geographical locations

No Comments

No Known Activations