INDEX

Explanations

repeated phrases that indicate a condition or state

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Manip

-0.16

MBER

-0.16

ushman

-0.15

amon

-0.15

Ð°Ð½ÑĮ

-0.14

 cumpl

-0.14

 Manip

-0.14

_Item

-0.14

ÑĥÑĩÐ°

-0.13

ason

-0.13

POSITIVE LOGITS

til

0.16

atted

0.15

bac

0.14

Ð¾ÑĢÐ°Ð·

0.14

owitz

0.14

erais

0.14

rel

0.14

aÄį

0.14

roz

0.14

_sequences

0.13

Activations Density 0.573%

repeated phrases that indicate a condition or state

No Comments

No Known Activations