INDEX

Explanations

punctuation and expressive elements in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ãģıãĤĮãĤĭ

-0.15

jer

-0.15

ÏİÏģÎ±

-0.14

ble

-0.14

ovic

-0.14

Enc

-0.14

 Medina

-0.13

ãģıãĤĮãģŁ

-0.13

ãĥĹãĥª

-0.13

ENC

-0.13

POSITIVE LOGITS

orno

0.16

à¥ĩà¤¬

0.15

erokee

0.15

 Anast

0.15

vana

0.15

íħ

0.14

Inflater

0.14

adil

0.14

apgolly

0.14

adio

0.13

Activations Density 0.013%

punctuation and expressive elements in the text

No Comments

No Known Activations