INDEX

Explanations

phrases indicating uncertainty or ambiguity regarding details or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

.defer

-0.15

 Latitude

-0.15

embre

-0.14

ETO

-0.14

HORT

-0.14

erez

-0.14

ernes

-0.14

eyh

-0.13

ifacts

-0.13

å¾½

-0.13

POSITIVE LOGITS

 exactly

0.19

 exact

0.18

 Exactly

0.18

Exactly

0.16

exact

0.16

 unknown

0.15

 precisely

0.15

pell

0.15

 extent

0.15

uilder

0.15

Activations Density 0.247%

phrases indicating uncertainty or ambiguity regarding details or conditions

No Comments

No Known Activations