INDEX

Explanations

references to workflows and workarounds in processes or systems

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

wal

-0.16

ushima

-0.15

ibar

-0.15

itus

-0.14

Ãłm

-0.14

_bt

-0.14

 èī¯

-0.14

Geo

-0.14

ican

-0.14

ate

-0.14

POSITIVE LOGITS

anova

0.17

ries

0.17

çª

0.15

olygon

0.15

ispens

0.15

spi

0.15

ool

0.15

 dopad

0.15

ureau

0.15

DEFINE

0.15

Activations Density 0.004%

references to workflows and workarounds in processes or systems

No Comments

No Known Activations