INDEX

Explanations

phrases that indicate causal relationships or origins

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

imson

-0.17

.infinity

-0.16

opis

-0.16

alama

-0.15

ersh

-0.15

ainen

-0.15

ulumi

-0.14

eton

-0.14

¹

-0.14

iniz

-0.14

POSITIVE LOGITS

 fact

0.20

:↵

0.16

Ã¡Å¾

0.16

fact

0.15

:↵↵

0.15

ager

0.14

mir

0.14

Descriptors

0.14

 having

0.14

Activations Density 0.127%

phrases that indicate causal relationships or origins

No Comments

No Known Activations