INDEX

Explanations

references to stock photography and image sources

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

 official

-0.17

illos

-0.16

ita

-0.15

enk

-0.15

leh

-0.14

 Official

-0.14

leigh

-0.14

gn

-0.14

ogl

-0.14

POSITIVE LOGITS

ERSIST

0.16

Â¤Â¤

0.16

Ð½Ð¸Ð½

0.16

[result

0.16

npos

0.15

 royalty

0.15

alim

0.15

ADDE

0.14

Routine

0.14

ystone

0.14

Activations Density 0.014%

references to stock photography and image sources

No Comments

No Known Activations