INDEX

Explanations

various names and terms related to popular culture, including media and entertainment references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ã¤m

-0.16

Ã¤tt

-0.16

stin

-0.16

rike

-0.14

alm

-0.14

inch

-0.14

ird

-0.14

ute

-0.14

asn

-0.14

aths

-0.14

POSITIVE LOGITS

Luc

0.14

 cork

0.14

.scalablytyped

0.14

Demand

0.14

0.13

ÃĹ↵↵

0.13

Hor

0.13

Zy

0.13

0.12

Activations Density 0.061%

various names and terms related to popular culture, including media and entertainment references

No Comments

No Known Activations