INDEX

Explanations

references to organizational branches or divisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jour

-0.19

oken

-0.16

çħ§

-0.15

ryo

-0.14

pel

-0.14

osis

-0.14

cents

-0.14

acists

-0.14

abis

-0.14

ropolis

-0.14

POSITIVE LOGITS

(branch

0.28

/Branch

0.26

(es

0.26

 Branch

0.25

 branch

0.24

branch

0.24

.branch

0.23

.Branch

0.23

es

0.22

 branches

0.20

Activations Density 0.016%

references to organizational branches or divisions

No Comments

No Known Activations