INDEX

Explanations

past experiences related to observations of media, performances, or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

orph

-0.15

ocker

-0.15

 corners

-0.15

lico

-0.14

 opport

-0.14

 pstmt

-0.14

orgot

-0.13

isd

-0.13

 corner

-0.13

POSITIVE LOGITS

 vÅ¯bec

0.19

ä¹ĭä¸Ģ

0.16

ÙģÙĪ

0.15

 EVER

0.15

athi

0.15

akk

0.14

jam

0.14

elines

0.14

loha

0.14

ERNEL

0.14

Activations Density 0.040%

past experiences related to observations of media, performances, or events

No Comments

No Known Activations