INDEX

Explanations

expressions of gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

lint

-0.15

lements

-0.15

ungen

-0.14

pais

-0.14

XE

-0.14

ipur

-0.14

XT

-0.14

unnable

-0.14

 parch

-0.14

atum

-0.14

POSITIVE LOGITS

 Aires

0.15

VICE

0.15

ÙĪÙĦÙĩ

0.15

iner

0.14

 doma

0.14

lef

0.14

loth

0.14

ine

0.14

 ValueType

0.13

 Jenner

0.13

Activations Density 0.047%

expressions of gratitude

No Comments

No Known Activations