INDEX

Explanations

specific labels or titles, particularly related to academic or professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

errer

-0.15

ince

-0.15

ens

-0.15

adian

-0.15

anson

-0.14

ensa

-0.14

ensed

-0.14

ains

-0.14

Ã¦r

-0.14

imates

-0.14

POSITIVE LOGITS

 Leer

0.15

onne

0.15

ologie

0.14

sumer

0.14

contri

0.14

otent

0.14

inth

0.14

èĸ

0.14

ote

0.13

aub

0.13

Activations Density 0.063%

specific labels or titles, particularly related to academic or professional contexts

No Comments

No Known Activations