INDEX

Explanations

phrases that express opinions or evaluations about events or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ayne

-0.16

åĿ¡

-0.15

LETE

-0.15

.synthetic

-0.15

swire

-0.14

è¦

-0.14

.'/'.$

-0.14

ÏĥÎ¹Î±

-0.14

 jspb

-0.14

 dele

-0.14

POSITIVE LOGITS

0.17

rah

0.15

0.14

ÐºÐ°ÑĢ

0.14

ims

0.14

ward

0.14

Ø¬Ùħ

0.14

uyáº¿t

0.13

thr

0.13

Activations Density 1.268%

phrases that express opinions or evaluations about events or experiences

No Comments

No Known Activations