INDEX

Explanations

phrases indicating victories or successes related to policy and legal outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

oppable

-0.14

iffs

-0.14

bal

-0.14

ÙħÙħ

-0.13

vur

-0.13

 Beaver

-0.13

ãĤĥ

-0.13

_ONCE

-0.13

fcn

-0.13

.opts

-0.13

POSITIVE LOGITS

 victory

0.46

 victories

0.39

 Victory

0.35

 triumph

0.34

win

0.33

 achievement

0.32

 accomplishment

0.30

 wins

0.29

 successes

0.27

èĥľ

0.26

Activations Density 0.184%

phrases indicating victories or successes related to policy and legal outcomes

No Comments

No Known Activations