INDEX

Explanations

phrases indicating legal or judicial outcomes and decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ahn

-0.15

USTER

-0.14

 hang

-0.14

erville

-0.14

avi

-0.14

czy

-0.14

-0.13

rina

-0.13

emer

-0.13

POSITIVE LOGITS

alist

0.15

umo

0.15

Wer

0.14

ighth

0.14

.virtual

0.14

uden

0.14

ãĥ¼ãĥ

0.14

VENTORY

0.14

akening

0.14

edBy

0.13

Activations Density 0.030%

phrases indicating legal or judicial outcomes and decision-making processes

No Comments

No Known Activations