INDEX

Explanations

geographical locations and their associated descriptors or boundaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

olio

-0.16

ubber

-0.15

zb

-0.15

ouis

-0.14

 supreme

-0.13

rub

-0.13

çĽ¤

-0.13

 Äįin

-0.13

 fatty

-0.12

POSITIVE LOGITS

spd

0.15

IMENT

0.15

ramer

0.15

yme

0.14

 district

0.14

ottage

0.14

ammad

0.14

oggled

0.14

imen

0.14

Liked

0.14

Activations Density 0.079%

geographical locations and their associated descriptors or boundaries

No Comments

No Known Activations