INDEX

Explanations

strong statements opposing violence and advocating for human rights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

inding

-0.14

 quadr

-0.14

 really

-0.14

 æĿİ

-0.14

inda

-0.14

 exactly

-0.14

 hardly

-0.14

-0.13

uben

-0.13

Tap

-0.13

POSITIVE LOGITS

 tolerate

0.25

 toler

0.24

 acceptable

0.24

 tolerated

0.23

_tolerance

0.22

 tolerance

0.21

Accept

0.21

tol

0.20

 Accept

0.20

 ACCEPT

0.20

Activations Density 0.208%

strong statements opposing violence and advocating for human rights

No Comments

No Known Activations