INDEX

Explanations

terms related to requirements and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

pector

-0.16

phere

-0.16

chner

-0.15

olla

-0.15

ãĤĽ

-0.15

chter

-0.14

lest

-0.14

ispens

-0.14

esso

-0.14

aya

-0.14

POSITIVE LOGITS

 everywhere

0.14

otics

0.13

 Schwartz

0.13

Ð°Ð»Ð¸

0.13

atk

0.13

 Chung

0.13

ABI

0.13

ddb

0.13

0.12

 Lever

0.12

Activations Density 0.397%

terms related to requirements and conditions

No Comments

No Known Activations