INDEX

Explanations

references to animal handling and experimentation safety

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

arding

-0.14

Ð¾ÑĢÐ°

-0.14

 oceans

-0.14

 Mens

-0.14

avel

-0.13

 bump

-0.13

ext

-0.13

ripe

-0.13

DMA

-0.13

POSITIVE LOGITS

viv

0.24

 experiments

0.23

 experimentation

0.23

experiment

0.22

 Experiment

0.21

 Experimental

0.21

 experiment

0.21

Experimental

0.21

Experiment

0.20

 procedures

0.20

Activations Density 0.016%

references to animal handling and experimentation safety

No Comments

No Known Activations