INDEX

Explanations

references to a specific series of events or items related to "The Last" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

EMPLARY

-0.17

cheme

-0.16

orgen

-0.15

è¨³

-0.15

posite

-0.15

licant

-0.14

omen

-0.14

thes

-0.14

pring

-0.14

POSITIVE LOGITS

-minute

0.36

est

0.31

ingly

0.28

minute

0.24

.fm

0.24

 resort

0.24

 ditch

0.22

 straw

0.21

 remaining

0.20

 Resort

0.20

Activations Density 0.059%

references to a specific series of events or items related to "The Last" in various contexts

No Comments

No Known Activations