INDEX

Explanations

numerical identifiers related to research data or articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 reminis

-0.16

-0.15

arent

-0.15

-0.14

_VOID

-0.14

enger

-0.14

uble

-0.14

POSITIVE LOGITS

 three

0.21

three

0.21

 five

0.20

 four

0.20

four

0.20

0.19

 fourth

0.18

 FOUR

0.18

five

0.18

 third

0.17

Activations Density 0.124%

numerical identifiers related to research data or articles

No Comments

No Known Activations