INDEX

Explanations

phrases and concepts related to inversion or negative changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

dac

-0.14

-upper

-0.14

atri

-0.14

lescope

-0.14

iran

-0.14

ampo

-0.13

IODevice

-0.13

.upper

-0.13

dbo

-0.13

ursor

-0.13

POSITIVE LOGITS

 down

1.71

 Down

1.52

down

1.45

Down

1.44

-down

1.43

 DOWN

1.38

_down

1.23

DOWN

1.21

.down

1.19

_DOWN

1.02

Activations Density 1.147%

phrases and concepts related to inversion or negative changes

No Comments

No Known Activations