INDEX

Explanations

references to various series, likely indicating discussions about media or product collections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ìĦľ

-0.19

ERS

-0.18

agers

-0.18

ìĦľëĬĶ

-0.17

ager

-0.16

 slee

-0.16

Ð¾Ð¼ÐµÑĢ

-0.16

ers

-0.15

erring

-0.15

bridge

-0.15

POSITIVE LOGITS

icals

0.19

iyas

0.17

 finale

0.16

bz

0.16

ical

0.15

AFX

0.15

/type

0.15

ibility

0.14

iy

0.14

sing

0.14

Activations Density 0.032%

references to various series, likely indicating discussions about media or product collections

No Comments

No Known Activations