INDEX

Explanations

references to strength and physical capabilities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

izabeth

-0.15

atches

-0.15

IFO

-0.14

portun

-0.14

INTERFACE

-0.14

dra

-0.14

subpackage

-0.14

ervice

-0.13

pec

-0.13

oma

-0.13

POSITIVE LOGITS

ray

0.15

SetName

0.15

Strength

0.15

rad

0.14

ripe

0.14

lessly

0.14

 ÐŁÑĢÐ°

0.14

istrovstvÃŃ

0.14

owie

0.14

essel

0.14

Activations Density 0.008%

references to strength and physical capabilities

No Known Activations