INDEX

Explanations

terms related to legal and financial outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

cer

-0.14

 proced

-0.14

CLOCKS

-0.13

 GÃ¼

-0.13

Ä°K

-0.12

Unnamed

-0.12

ditor

-0.12

dec

-0.12

Ø¯Ø«

-0.12

POSITIVE LOGITS

cing

0.15

MMdd

0.14

ictionary

0.14

.reducer

0.13

åĥı

0.13

 jestli

0.13

arend

0.13

efa

0.13

izzare

0.13

presence

0.13

Activations Density 0.029%

terms related to legal and financial outcomes

No Comments

No Known Activations