INDEX

Explanations

punctuation marks used in dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

tps

-0.18

rieve

-0.17

-0.16

ttp

-0.15

rieved

-0.14

 turb

-0.14

 alter

-0.14

pic

-0.14

Ret

-0.13

Lay

-0.13

POSITIVE LOGITS

UPER

0.15

å¹³æĪĲ

0.14

 Maiden

0.14

SEA

0.14

enser

0.14

byn

0.14

áº¯p

0.14

ibil

0.14

_Se

0.13

sea

0.13

Activations Density 0.000%

punctuation marks used in dialogue

No Comments

No Known Activations