INDEX

Explanations

references to media sources and platforms within articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hare

-0.16

cente

-0.15

odge

-0.15

çıł

-0.14

iene

-0.14

 ÐĺÑģÐ¿

-0.14

aters

-0.14

_PROTO

-0.13

cent

-0.13

 Warren

-0.13

POSITIVE LOGITS

 pregn

0.15

crate

0.14

ypy

0.14

ÅŁam

0.14

 âĹĦ

0.14

çĽ

0.14

:Register

0.13

 :č↵

0.13

urret

0.13

andest

0.13

Activations Density 0.129%

references to media sources and platforms within articles

No Comments

No Known Activations