INDEX

Explanations

specific programming or markup elements used in technical documentation and code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

vak

-0.17

Vak

-0.16

oulos

-0.15

µ

-0.15

Î²Î¬

-0.15

olid

-0.15

DP

-0.14

igan

-0.14

rench

-0.14

POSITIVE LOGITS

 center

0.18

center

0.17

ighb

0.17

zos

0.17

icher

0.15

Sic

0.15

-center

0.15

 Single

0.15

 centre

0.15

burgh

0.15

Activations Density 0.017%

specific programming or markup elements used in technical documentation and code

No Comments

No Known Activations