INDEX

Explanations

quoted speech and statements from individuals

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Replies

-0.15

iros

-0.14

utan

-0.14

.nano

-0.14

ondo

-0.14

zac

-0.14

anki

-0.14

ItemAt

-0.14

_reply

-0.14

Eis

-0.13

POSITIVE LOGITS

arf

0.16

.AF

0.15

 Sunder

0.14

ushi

0.14

rosse

0.14

irected

0.14

($.

0.13

iale

0.13

 Shemale

0.13

kw

0.13

Activations Density 0.071%

quoted speech and statements from individuals

No Comments

No Known Activations