INDEX

Explanations

key terms related to scientific topics and their applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ahir

-0.16

iasi

-0.15

oran

-0.15

RuleContext

-0.15

ayd

-0.15

ATIC

-0.14

Ã¡lido

-0.14

 McKenzie

-0.14

æ£

-0.14

.StatusCode

-0.13

POSITIVE LOGITS

§è¡Į

0.16

est

0.15

 Schultz

0.15

eyim

0.14

 AndAlso

0.14

ìłĢ

0.13

ishi

0.13

 unst

0.13

 Crown

0.13

ti

0.13

Activations Density 0.084%

key terms related to scientific topics and their applications

No Comments

No Known Activations