INDEX

Explanations

words that denote geographical locations or entities associated with place names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ÑĢÐ°Ð±

-0.15

 Woods

-0.14

rani

-0.14

uck

-0.14

 Tucker

-0.14

UCK

-0.13

ãĥĩãĥ«

-0.13

ics

-0.13

yth

-0.13

unning

-0.13

POSITIVE LOGITS

erot

0.16

AsyncResult

0.15

 seedu

0.15

ields

0.15

stantiateViewController

0.14

ÄĽr

0.14

.struct

0.14

OV

0.14

Ã©ny

0.14

iator

0.14

Activations Density 0.314%

words that denote geographical locations or entities associated with place names

No Comments

No Known Activations