INDEX

Explanations

conjunctions and phrases related to logical connections and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

isc

-0.18

em

-0.15

ony

-0.15

oda

-0.15

app

-0.15

 attempts

-0.14

bre

-0.14

avenport

-0.14

ano

-0.14

ilton

-0.14

POSITIVE LOGITS

.Objects

0.17

-threat

0.17

 frec

0.16

 hadn

0.16

perty

0.16

hud

0.16

uetype

0.15

adera

0.15

Ð»Ð¾ÑĤ

0.15

 frequently

0.15

Activations Density 0.012%

conjunctions and phrases related to logical connections and conditions

No Comments

No Known Activations