INDEX

Explanations

phrases indicating prior mentions or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

isle

-0.14

uj

-0.14

ISR

-0.14

Ask

-0.13

uel

-0.13

Gad

-0.13

plete

-0.13

ir

-0.13

est

-0.13

ette

-0.13

POSITIVE LOGITS

 above

0.21

Above

0.19

_above

0.18

 earlier

0.17

above

0.17

 Above

0.16

.FieldName

0.16

ä»¥ä¸Ĭ

0.16

 Ð²ÑĭÑĪÐµ

0.16

zung

0.16

Activations Density 0.037%

phrases indicating prior mentions or references

No Comments

No Known Activations

phrases indicating prior mentions or references

No Comments

No Known Activations