INDEX

Explanations

communication of findings and information sharing in a formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

quet

-0.18

lod

-0.18

lod

-0.15

gne

-0.15

ivol

-0.14

lob

-0.14

 volumes

-0.14

arto

-0.14

lon

-0.14

tour

-0.14

POSITIVE LOGITS

 Relay

0.17

bara

0.16

relay

0.15

trl

0.15

0.14

egg

0.14

ÑĩÐ¸

0.14

Î¹Ïĩ

0.14

veyor

0.14

phyl

0.14

Activations Density 0.393%

communication of findings and information sharing in a formal context

No Comments

No Known Activations