INDEX

Explanations

expressions of gratitude and recognition in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ddy

-0.16

ekler

-0.14

osity

-0.14

ãĥ¼ãĥ³

-0.14

 cáº§u

-0.14

roup

-0.13

 BorderRadius

-0.13

_tree

-0.12

Ľå»º

-0.12

.MaxLength

-0.12

POSITIVE LOGITS

ãĤ¢ãĥ¼

0.16

aut

0.14

 Nack

0.14

ãģĿãģĨãģª

0.14

GetMethod

0.14

apos

0.14

 slee

0.13

_INST

0.13

_SF

0.13

áº¯c

0.13

Activations Density 0.584%

expressions of gratitude and recognition in statements

No Comments

No Known Activations