INDEX

Explanations

the term "Other" and its variations in relation to various contexts or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ker

-0.14

ÙĦÙħ

-0.14

.scalablytyped

-0.14

rum

-0.13

 ÎĳÏģÏĩ

-0.13

aci

-0.13

.dispatchEvent

-0.13

-c

-0.13

-qu

-0.13

ë³´

-0.13

POSITIVE LOGITS

 Chapman

0.15

Ø¡

0.15

mers

0.15

ewise

0.14

ackbar

0.14

urer

0.14

tracer

0.14

INLINE

0.14

 similar

0.13

edge

0.13

Activations Density 0.052%

the term "Other" and its variations in relation to various contexts or categories

No Comments

No Known Activations