INDEX

Explanations

conversational phrases that address or engage the reader directly

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

igate

-0.15

ours

-0.14

itos

-0.14

inters

-0.14

iss

-0.14

 Record

-0.14

hi

-0.14

 record

-0.13

avier

-0.13

Dee

-0.13

POSITIVE LOGITS

/stats

0.15

ãĥ«ãĥķ

0.14

OLID

0.14

Frozen

0.14

wnd

0.14

scratch

0.14

-drop

0.14

ivic

0.14

ennen

0.14

Î²ÎŃÏģ

0.14

Activations Density 0.190%

conversational phrases that address or engage the reader directly

No Comments

No Known Activations