INDEX

Explanations

adjectives and descriptors that indicate quality or characteristics of objects and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

.SizeType

-0.15

ì²

-0.15

.SetToolTip

-0.14

-thumbnails

-0.13

orks

-0.13

_mgmt

-0.13

arel

-0.13

edla

-0.13

ĵ¨

-0.13

POSITIVE LOGITS

 looking

0.85

looking

0.79

-looking

0.72

 sounding

0.72

 Looking

0.65

Looking

0.61

 seeming

0.50

 smelling

0.44

 appearing

0.43

-fe

0.42

Activations Density 0.250%

adjectives and descriptors that indicate quality or characteristics of objects and experiences

No Comments

No Known Activations