INDEX

Explanations

transitional phrases indicating time or sequence of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Antar

-0.16

aq

-0.16

chal

-0.15

azole

-0.15

ubits

-0.14

uyo

-0.14

tons

-0.14

istas

-0.14

 Grade

-0.13

bru

-0.13

POSITIVE LOGITS

hin

0.17

SENT

0.15

 sadd

0.14

 Buen

0.14

 Eigen

0.14

estring

0.14

.databinding

0.14

hrad

0.14

 Smooth

0.14

 pacing

0.14

Activations Density 0.154%

transitional phrases indicating time or sequence of events

No Comments

No Known Activations