INDEX

Explanations

proper nouns, particularly names and titles

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

ulo

-0.16

iss

-0.15

-bodied

-0.15

zin

-0.15

iability

-0.15

led

-0.15

lessly

-0.15

aska

-0.14

zan

-0.14

POSITIVE LOGITS

errat

0.23

(mon

0.19

oton

0.19

gomery

0.19

serrat

0.18

roe

0.18

.Mon

0.17

trÃ©al

0.17

Ð¸ÑĤÐ¾ÑĢ

0.17

stery

0.17

Activations Density 0.050%

proper nouns, particularly names and titles

No Comments

No Known Activations