INDEX

Explanations

commas in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

minus

-0.15

 comprehension

-0.14

ippy

-0.14

ProcessEvent

-0.14

ElementException

-0.14

yr

-0.14

ovatel

-0.14

ramer

-0.14

 away

-0.13

PÅĻed

-0.13

POSITIVE LOGITS

 Mixed

0.15

bies

0.15

 Ruiz

0.14

bane

0.14

ãĥ³ãĤ¿

0.14

 Mock

0.14

olt

0.13

 Lucia

0.13

 Slee

0.13

Activations Density 0.036%

commas in text

No Comments

No Known Activations