INDEX

Explanations

calls to action related to contacting a service or making inquiries

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

/embed

-0.15

ikhail

-0.14

pir

-0.14

fe

-0.14

phinx

-0.14

èĹı

-0.13

ãĤĤãģ®

-0.13

era

-0.13

bol

-0.13

ERGE

-0.13

POSITIVE LOGITS

ãĥĭãĥĥãĤ¯

0.17

oldown

0.15

stants

0.15

ofil

0.15

ordova

0.14

acente

0.14

_MACRO

0.14

.double

0.14

racuse

0.14

ÛĮÙĦÛĮ

0.14

Activations Density 0.020%

calls to action related to contacting a service or making inquiries

No Comments

No Known Activations