INDEX

Explanations

phrases indicating a summary or explanation of a process

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

antlr

-0.16

 perhaps

-0.16

anna

-0.15

 mutlaka

-0.15

 åŁ

-0.15

alle

-0.15

ille

-0.14

isma

-0.14

HCI

-0.14

 bergen

-0.14

POSITIVE LOGITS

_except

0.15

anford

0.15

scopic

0.14

PTION

0.14

 Ð¶Ðµ

0.14

-ÑĤÐ°ÐºÐ¸

0.13

 glor

0.13

.heroku

0.13

NewLabel

0.13

elines

0.13

Activations Density 0.025%

phrases indicating a summary or explanation of a process

No Comments

No Known Activations