INDEX

Explanations

terms and concepts related to confidentiality and trade secrets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ande

-0.15

uhn

-0.15

utdown

-0.15

 Morton

-0.14

aku

-0.14

reat

-0.14

elman

-0.14

olit

-0.14

XMLLoader

-0.14

vore

-0.14

POSITIVE LOGITS

 trim

0.17

Dam

0.17

chio

0.16

 Trim

0.15

 Dram

0.15

ep

0.14

ê¸Ī

0.14

 spread

0.14

dam

0.14

bro

0.14

Activations Density 0.019%

terms and concepts related to confidentiality and trade secrets

No Comments

No Known Activations