INDEX

Explanations

phrases indicating recurrence or additional information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

luv

-0.15

atz

-0.15

.volley

-0.15

ripe

-0.14

arpa

-0.14

æ£

-0.14

ãĥªãĥ³

-0.14

ÑĨÐ²ÐµÑĤ

-0.14

ãĤŃãĥ³ãĤ°

-0.14

ASTER

-0.13

POSITIVE LOGITS

 paralle

0.17

asket

0.17

-INF

0.16

INI

0.15

xit

0.15

icode

0.15

ernal

0.14

ÅĤem

0.14

ÑĤÑĢÐ¾

0.14

ideo

0.13

Activations Density 0.127%

phrases indicating recurrence or additional information

No Comments

No Known Activations