INDEX

Explanations

dates and related numerical information

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

iaux

-0.19

icast

-0.17

ialog

-0.16

chip

-0.15

asion

-0.15

alez

-0.15

acket

-0.15

CI

-0.15

ergus

-0.15

ariate

-0.15

POSITIVE LOGITS

odos

0.17

cab

0.14

 Jeho

0.14

ANGLE

0.14

ãĥ£

0.13

 Rosenstein

0.13

 MetroFramework

0.13

dale

0.13

_HIDDEN

0.13

pap

0.13

Activations Density 0.025%

dates and related numerical information

No Comments

No Known Activations