INDEX

Explanations

references to wildlife incidents and human interactions with wild animals

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

Pig

-0.16

pig

-0.16

 wolf

-0.15

.prototype

-0.15

 Wolf

-0.15

çĮª

-0.15

 licking

-0.14

 licked

-0.14

 shark

-0.14

pig

-0.14

POSITIVE LOGITS

 capture

0.22

captures

0.22

 captures

0.21

 euth

0.21

capture

0.20

 Capture

0.20

 handling

0.20

net

0.19

-net

0.18

æįķ

0.18

Activations Density 0.128%

references to wildlife incidents and human interactions with wild animals

No Comments

No Known Activations