INDEX

Explanations

numeric values and measurements related to products or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ourn

-0.16

.parsers

-0.15

hart

-0.15

labs

-0.15

áº¡n

-0.15

oproject

-0.15

slashes

-0.15

beck

-0.15

ernes

-0.15

 Leap

-0.14

POSITIVE LOGITS

ÑĨÐ¸Ð½

0.18

 Teeth

0.17

 stage

0.17

.stage

0.16

 Stage

0.16

-lite

0.16

 teeth

0.15

 layer

0.15

 channel

0.15

Activations Density 0.110%

numeric values and measurements related to products or items

No Comments

No Known Activations