INDEX

Explanations

phrases related to legal or social issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ieÅ¼

-0.16

opia

-0.15

áºŃy

-0.15

eway

-0.15

 lantern

-0.14

 Lantern

-0.14

shiv

-0.14

agina

-0.14

/rc

-0.14

á»ĭp

-0.14

POSITIVE LOGITS

ADOS

0.18

reb

0.17

0.15

Woo

0.15

erd

0.14

.ov

0.14

reb

0.14

Uns

0.14

ipl

0.14

 sources

0.14

Activations Density 0.486%

phrases related to legal or social issues

No Comments

No Known Activations