INDEX

Explanations

frequent references to specific date formats and numerical identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

IgnoreCase

-0.17

ahan

-0.16

lier

-0.16

uhan

-0.16

gie

-0.15

solete

-0.15

wij

-0.15

ultz

-0.15

DTV

-0.14

edException

-0.14

POSITIVE LOGITS

th

0.22

ors

0.15

âĢ³

0.15

à¸§

0.15

ne

0.15

ÛĮØ§

0.15

ively

0.14

ailable

0.14

tru

0.14

aged

0.14

Activations Density 0.036%

frequent references to specific date formats and numerical identifiers

No Comments

No Known Activations