INDEX

Explanations

references to specific names or entities, particularly related to people and their surnames

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

ledge

-0.16

naire

-0.15

 favor

-0.15

kish

-0.15

favor

-0.14

resi

-0.14

gere

-0.14

witter

-0.14

 Certificate

-0.14

hoo

-0.14

POSITIVE LOGITS

egov

0.19

loom

0.19

Her

0.17

itage

0.17

ules

0.17

amient

0.16

aint

0.16

Her

0.16

ogs

0.15

encia

0.15

Activations Density 0.023%

references to specific names or entities, particularly related to people and their surnames

No Comments

No Known Activations