INDEX

Explanations

instances of Latin or placeholder text commonly used in design and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

gnore

-0.17

onaut

-0.16

olta

-0.15

urette

-0.15

ander

-0.15

.AWS

-0.15

patch

-0.14

çĿ

-0.14

boru

-0.14

inges

-0.14

POSITIVE LOGITS

RLF

0.15

iles

0.15

Ħ

0.14

ummy

0.14

Ì£

0.13

sequ

0.13

Lorem

0.13

ills

0.13

 Denn

0.13

Activations Density 0.004%

instances of Latin or placeholder text commonly used in design and documentation

No Comments

No Known Activations