INDEX

Explanations

references to key components and elements within systems or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

orum

-0.16

hawks

-0.15

presso

-0.15

ucc

-0.15

_normals

-0.15

hart

-0.15

 grav

-0.15

-0.14

okers

-0.14

POSITIVE LOGITS

/main

0.28

enance

0.21

/root

0.17

AxisAlignment

0.17

-secondary

0.17

AxisSize

0.17

eryl

0.16

 axis

0.15

/master

0.15

frame

0.15

Activations Density 0.097%

references to key components and elements within systems or structures

No Comments

No Known Activations