INDEX

Explanations

constructs and concepts related to programming, particularly focusing on global variables and data tracking in classes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

_HINT

-0.17

 ÐĳÐ¾Ð³

-0.16

anka

-0.16

pekt

-0.15

tempts

-0.15

Bog

-0.14

ammed

-0.14

_BATCH

-0.14

ift

-0.14

ulls

-0.14

POSITIVE LOGITS

steen

0.16

igu

0.16

 stores

0.16

undi

0.16

ilar

0.15

pio

0.14

ÅĻel

0.14

 store

0.14

_store

0.14

ÑĪÐ¾Ð²

0.14

Activations Density 0.293%

constructs and concepts related to programming, particularly focusing on global variables and data tracking in classes

No Comments

No Known Activations