INDEX

Explanations

expressions of frustration or intense emotion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ÏĢÎ¯

-0.15

ockets

-0.15

bah

-0.14

 Terra

-0.14

isle

-0.14

atches

-0.13

manda

-0.13

zbo

-0.13

zie

-0.13

POSITIVE LOGITS

auer

0.20

ation

0.15

ankan

0.15

=-=-

0.14

 Kenn

0.14

near

0.14

 IEnumerator

0.14

acades

0.13

abit

0.13

ìĨĲ

0.13

Activations Density 0.019%

expressions of frustration or intense emotion

No Comments

No Known Activations