INDEX

Explanations

references to political leaders and their actions or appearances

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

-0.16

æİĽ

-0.15

nds

-0.15

haps

-0.15

 independence

-0.14

haus

-0.14

MUT

-0.14

stÃ¤nd

-0.14

chor

-0.14

UNS

-0.14

POSITIVE LOGITS

-sama

0.17

andan

0.16

 Schwarz

0.15

.scalablytyped

0.15

dk

0.15

 Dank

0.14

zig

0.14

ienen

0.14

 personally

0.14

BackColor

0.14

Activations Density 0.299%

references to political leaders and their actions or appearances

No Comments

No Known Activations