INDEX

Explanations

technical terms related to memory management and data structures

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

activex

-0.16

[string

-0.16

anders

-0.15

angs

-0.14

ç©

-0.14

[strlen

-0.14

akeup

-0.14

OLON

-0.14

ãĥ¼ãĥ

-0.14

¶Ī

-0.14

POSITIVE LOGITS

 Unsafe

0.19

Unsafe

0.18

 memory

0.18

Stride

0.17

 Memory

0.17

nio

0.17

 stride

0.17

 buffer

0.16

 direct

0.16

 strides

0.16

Activations Density 0.057%

technical terms related to memory management and data structures

No Comments

No Known Activations