INDEX

Explanations

phrases related to completion or filling in missing information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

shaw

-0.18

borg

-0.18

HIR

-0.16

ÙģØ´

-0.16

ÑĤÑĢÐ¾

-0.15

aca

-0.15

auc

-0.15

entionPolicy

-0.14

lyph

-0.14

trl

-0.14

POSITIVE LOGITS

0.17

0.15

 Fill

0.15

 regional

0.15

oles

0.15

reg

0.14

ãĥ¼ãĥĪ

0.14

 fill

0.14

Activations Density 0.019%

phrases related to completion or filling in missing information

No Comments

No Known Activations