INDEX

Explanations

references to previous discussions or mentions made in a conversational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

fly

-0.16

armac

-0.15

led

-0.15

eve

-0.14

ul

-0.14

ãĥ©ãĥ³ãĥī

-0.14

à¤Ĥà¤¬

-0.14

Ð²ÐµÐ´

-0.13

 dá»±

-0.13

POSITIVE LOGITS

gay

0.16

 Ãĸr

0.16

ickerView

0.16

Ã½t

0.15

.enumer

0.15

vier

0.15

quence

0.15

 shaved

0.14

Ã¦re

0.14

afe

0.14

Activations Density 0.530%

references to previous discussions or mentions made in a conversational context

No Comments

No Known Activations