INDEX

Explanations

punctuation marks and their associated significance 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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.15

/fw

-0.15

itbart

-0.15

 forks

-0.15

.scalablytyped

-0.15

Î¶Î±

-0.15

Jad

-0.14

.bunifuFlatButton

-0.14

viron

-0.14

geois

-0.14

POSITIVE LOGITS

çª

0.16

kili

0.15

 Hermes

0.15

AVIS

0.15

éĽĨ

0.15

asca

0.14

OTES

0.14

ymes

0.14

olle

0.14

ãĤ·ãĥ¼

0.14

Activations Density 0.210%

punctuation marks and their associated significance in the text

No Comments

No Known Activations