INDEX

Explanations

programming constructs and operations related to memory management and data manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ê¶Į

-0.18

ussen

-0.17

Invoker

-0.16

 Alic

-0.15

elli

-0.14

.Toolkit

-0.14

enco

-0.14

estone

-0.14

ylko

-0.14

ardon

-0.14

POSITIVE LOGITS

ormsg

0.17

Î±Î¹Î½

0.15

 Dodd

0.14

 Gregg

0.14

igator

0.14

.semantic

0.14

Î³Î¹

0.14

_INITIALIZER

0.14

itchen

0.14

ãĥ¯

0.13

Activations Density 0.038%

programming constructs and operations related to memory management and data manipulation

No Comments

No Known Activations