INDEX

Explanations

key figures and events related to specific organizations and their leadership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

UFFIX

-0.14

&action

-0.14

Ã¬nh

-0.14

<context

-0.14

iae

-0.14

vale

-0.13

idf

-0.13

laps

-0.13

RowIndex

-0.13

reich

-0.13

POSITIVE LOGITS

hin

0.15

hor

0.14

has

0.14

ner

0.14

ãĤ§

0.14

ãĥ£

0.14

hetto

0.13

ä¼į

0.13

is

0.13

Activations Density 0.822%

key figures and events related to specific organizations and their leadership

No Comments

No Known Activations